LLM-driven dialog systems are used in a diverse set of applications, ranging from healthcare to customer service. However, given their generalization capability, it is difficult to ensure that these chatbots stay within the boundaries of the specialized domains, potentially resulting in inaccurate information and irrelevant responses. This paper introduces an unsupervised approach for automatically inducing domain-specific dialog flows that can be used to constrain LLM-based chatbots. We introduce two variants of dialog flow based on the availability of in-domain conversation instances. Through human and automatic evaluation over 24 dialog domains, we demonstrate that our high-quality data-guided dialog flows achieve better domain coverage, thereby overcoming the need for extensive manual crafting of such flows.

Large pre-trained language models (PLMs) have been shown to retain implicit knowledge within their parameters. To enhance this implicit knowledge, we propose Knowledge Injection into Language Models (KILM), a novel approach that injects entity-related knowledge into encoder-decoder PLMs, via a generative knowledge infilling objective through continued pre-training. This is done without architectural modifications to the PLMs or adding additional parameters. Experimental results over a suite of knowledge-intensive tasks spanning numerous datasets show that KILM enables models to retain more knowledge and hallucinate less while preserving their original performance on general NLU and NLG tasks. KILM also demonstrates improved zero-shot performances on tasks such as entity disambiguation, outperforming state-of-the-art models having 30x more parameters.

Collecting high quality conversational data can be very expensive for most applications and infeasible for others due to privacy, ethical, or similar concerns. A promising direction to tackle this problem is to generate synthetic dialogues by prompting large language models. In this work, we use a small set of expert-written conversations as in-context examples to synthesize a social conversation dataset using prompting. We perform several thorough evaluations of our synthetic conversations compared to human-collected conversations. This includes various dimensions of conversation quality with human evaluation directly on the synthesized conversations, and interactive human evaluation of chatbots fine-tuned on the synthetically generated dataset. We additionally demonstrate that this prompting approach is generalizable to multi-party conversations, providing potential to create new synthetic data for multi-party tasks. Our synthetic multi-party conversations were rated more favorably across all measured dimensions compared to conversation excerpts sampled from a human-collected multi-party dataset.

While large neural-based conversational models have become increasingly proficient dialogue agents, recent work has highlighted safety issues with these systems. For example, these systems can be goaded into generating toxic content, often perpetuating social biases or stereotypes. We investigate a retrieval-based approach for reducing bias and toxicity in responses from chatbots. It uses in-context learning to steer a model towards safer generations. Concretely, to generate a response to an unsafe dialogue context, we retrieve demonstrations of safe responses to similar dialogue contexts. We find our method performs competitively with existing approaches to dialogue safety without requiring training. We also show, using automatic and human evaluation, that reductions in toxicity obtained using our approach are not at the cost engagingness or coherency. Finally, we note our method can be used in compliment to existing dialogue safety approaches, such as RLHF.

Dialogue models are able to generate coherent and fluent responses, but they can still be challenging to control and may produce non-engaging, unsafe results. This unpredictability diminishes user trust and can hinder the use of the models in the real world. To address this, we introduce DialGuide, a novel framework for controlling dialogue model behavior using natural language rules, or guidelines. These guidelines provide information about the context they are applicable to and what should be included in the response, allowing the models to generate responses that are more closely aligned with the developer’s expectations and intent. We evaluate DialGuide on three tasks in open-domain dialogue response generation: guideline selection, response generation, and response entailment verification. Our dataset contains 10,737 positive and 15,467 negative dialogue context-response-guideline triplets across two domains - chit-chat and safety. We provide baseline models for the tasks and benchmark their performance. We also demonstrate that DialGuide is effective in the dialogue safety domain, producing safe and engaging responses that follow developer guidelines.

Task-oriented Dialogue (TOD) Systems aim to build dialogue systems that assist users in accomplishing specific goals, such as booking a hotel or a restaurant. Traditional TODs rely on domain-specific APIs/DBs or external factual knowledge to generate responses, which cannot accommodate subjective user requests (e.g.,”Is the WIFI reliable?” or “Does the restaurant have a good atmosphere?”). To address this issue, we propose a novel task of subjective-knowledge-based TOD (SK-TOD). We also propose the first corresponding dataset, which contains subjective knowledge-seeking dialogue contexts and manually annotated responses grounded in subjective knowledge sources. When evaluated with existing TOD approaches, we find that this task poses new challenges such as aggregating diverse opinions from multiple knowledge snippets. We hope this task and dataset can promote further research on TOD and subjective content understanding. The code and the dataset are available at https://github.com/alexa/dstc11-track5.

The bulk of work adapting transformer models to open-domain dialogue represents dialogue context as the concatenated set of turns in natural language. However, it is unclear if this is the best approach. In this work, we investigate this question by means of an empirical controlled experiment varying the dialogue context format from text-only formats (all recent utterances, summaries, selected utterances) as well as variants that are more structurally different (triples, AMR). We compare these formats based on fine-tuned model performance on two downstream tasks—knowledge selection and response generation. We find that simply concatenating the utterances works as a strong baseline in most cases, but is outperformed in longer contexts by a hybrid approach of combining a summary of the context with recent utterances. Through empirical analysis, our work highlights the need to examine the format of context representation and offers recommendations on adapting general-purpose language models to dialogue tasks.

Automatic Evaluation (AE) and Response Selection (RS) models assign quality scores to various candidate responses and rank them in conversational setups. Prior response ranking research compares various models’ performance on synthetically generated test sets. In this work, we investigate the performance of model-based reference-free AE and RS models on our constructed response ranking datasets that mirror real-case scenarios of ranking candidates during inference time. Metrics’ unsatisfying performance can be interpreted as their low generalizability over more pragmatic conversational domains such as human-chatbot dialogs. To alleviate this issue we propose a novel RS model called MERCY that simulates human behavior in selecting the best candidate by taking into account distinct candidates concurrently and learns to rank them. In addition, MERCY leverages natural language feedback as another component to help the ranking task by explaining why each candidate response is relevant/irrelevant to the dialog context. These feedbacks are generated by prompting large language models in a few-shot setup. Our experiments show the better performance of MERCY over baselines for the response ranking task in our curated realistic datasets.

Embodied task completion is a challenge where an agent in a simulated environment must predict environment actions to complete tasks based on natural language instructions and ego-centric visual observations. We propose a variant of this problem where the agent predicts actions at a higher level of abstraction called a plan, which helps make agent actions more interpretable and can be obtained from the appropriate prompting of large language models. We show that multimodal transformer models can outperform language-only models for this problem but fall significantly short of oracle plans. Since collecting human-human dialogues for embodied environments is expensive and time-consuming, we propose a method to synthetically generate such dialogues, which we then use as training data for plan prediction. We demonstrate that multimodal transformer models can attain strong zero-shot performance from our synthetic data, outperforming language-only models trained on human-human data.

Instruction-based multitasking has played a critical role in the success of large language models (LLMs) in multi-turn dialog applications. While publicly available LLMs have shown promising performance, when exposed to complex instructions with multiple constraints, they lag against state-of-the-art models like ChatGPT. In this work, we hypothesize that the availability of large-scale complex demonstrations is crucial in bridging this gap. Focusing on dialog applications, we propose a novel framework, CESAR, that unifies a large number of dialog tasks in the same format and allows programmatic induction of complex instructions without any manual effort. We apply CESAR on InstructDial, a benchmark for instruction-based dialog tasks. We further enhance InstructDial with new datasets and tasks and utilize CESAR to induce complex tasks with compositional instructions. This results in a new benchmark called InstructDial++, which includes 63 datasets with 86 basic tasks and 68 composite tasks. Through rigorous experiments, we demonstrate the scalability of CESAR in providing rich instructions. Models trained on InstructDial++ can follow compositional prompts, such as prompts that ask for multiple stylistic constraints.

This work focuses on in-context data augmentation for intent detection. Having found that augmentation via in-context prompting of large pre-trained language models (PLMs) alone does not improve performance, we introduce a novel approach based on PLMs and pointwise V-information (PVI), a metric that can measure the usefulness of a datapoint for training a model. Our method first fine-tunes a PLM on a small seed of training data and then synthesizes new datapoints - utterances that correspond to given intents. It then employs intent-aware filtering, based on PVI, to remove datapoints that are not helpful to the downstream intent classifier. Our method is thus able to leverage the expressive power of large language models to produce diverse training data. Empirical results demonstrate that our method can produce synthetic training data that achieve state-of-the-art performance on three challenging intent detection datasets under few-shot settings (1.28% absolute improvement in 5-shot and 1.18% absolute in 10-shot, on average) and perform on par with the state-of-the-art in full-shot settings (within 0.01% absolute, on average).

Providing conversation models with background knowledge has been shown to make open-domain dialogues more informative and engaging. Existing models treat knowledge selection as a sentence ranking or classification problem where each sentence is handled individually, ignoring the internal semantic connection between sentences. In this work, we propose to automatically convert the background knowledge documents into document semantic graphs and then perform knowledge selection over such graphs. Our document semantic graphs preserve sentence-level information through the use of sentence nodes and provide concept connections between sentences. We apply multi-task learning to perform sentence-level knowledge selection and concept-level knowledge selection, showing that it improves sentence-level selection. Our experiments show that our semantic graph-based knowledge selection improves over sentence selection baselines for both the knowledge selection task and the end-to-end response generation task on HollE and improves generalization on unseen topics in WoW.

Transformer-based models are not efficient in processing long sequences due to the quadratic space and time complexity of the self-attention modules. To address this limitation, Linformer and Informer reduce the quadratic complexity to linear (modulo logarithmic factors) via low-dimensional projection and row selection, respectively. These two models are intrinsically connected, and to understand their connection we introduce a theoretical framework of matrix sketching. Based on the theoretical analysis, we propose Skeinformer to accelerate self-attention and further improve the accuracy of matrix approximation to self-attention with column sampling, adaptive row normalization and pilot sampling reutilization. Experiments on the Long Range Arena benchmark demonstrate that our methods outperform alternatives with a consistently smaller time/space footprint.

Implicit knowledge, such as common sense, is key to fluid human conversations. Current neural response generation (RG) models are trained to generate responses directly, omitting unstated implicit knowledge. In this paper, we present Think-Before-Speaking (TBS), a generative approach to first externalize implicit commonsense knowledge (think) and use this knowledge to generate responses (speak). We argue that externalizing implicit knowledge allows more efficient learning, produces more informative responses, and enables more explainable models. We analyze different choices to collect knowledge-aligned dialogues, represent implicit knowledge, and transition between knowledge and dialogues. Empirical results show TBS models outperform end-to-end and knowledge-augmented RG baselines on most automatic metrics and generate more informative, specific, and commonsense-following responses, as evaluated by human annotators. TBS also generates knowledge that makes sense and is relevant to the dialogue around 85% of the time

While rich, open-domain textual data are generally available and may include interesting phenomena (humor, sarcasm, empathy, etc.) most are designed for language processing tasks, and are usually in a non-conversational format. In this work, we take a step towards automatically generating conversational data using Generative Conversational Networks, aiming to benefit from the breadth of available language and knowledge data, and train open domain social conversational agents. We evaluate our approach on conversations with and without knowledge on the Topical Chat dataset using automatic metrics and human evaluators. Our results show that for conversations without knowledge grounding, GCN can generalize from the seed data, producing novel conversations that are less relevant but more engaging and for knowledge-grounded conversations, it can produce more knowledge-focused, fluent, and engaging conversations. Specifically, we show that for open-domain conversations with 10% of seed data, our approach performs close to the baseline that uses 100% of the data, while for knowledge-grounded conversations, it achieves the same using only 1% of the data, on human ratings of engagingness, fluency, and relevance.

Embodied agents need to be able to interact in natural language – understanding task descriptions and asking appropriate follow up questions to obtain necessary information to be effective at successfully accomplishing tasks for a wide range of users. In this work, we propose a set of dialog acts for modelling such dialogs and annotate the TEACh dataset that includes over 3,000 situated, task oriented conversations (consisting of 39.5k utterances in total) with dialog acts. To our knowledge,TEACh-DA is the first large scale dataset of dialog act annotations for embodied task completion. Furthermore, we demonstrate the use of this annotated dataset in training models for tagging the dialog acts of a given utterance, predicting the dialog act of the next response given a dialog history, and use the dialog acts to guide agent’s non-dialog behaviour. In particular, our experiments on the TEACh Execution from Dialog History task where the model predicts the sequence of low level actions to be executed in the environment for embodied task completion, demonstrate that dialog acts can improve end performance by up to 2 points compared to the system without dialog acts.

Recent progress on neural approaches for language processing has triggered a resurgence of interest on building intelligent open-domain chatbots. However, even the state-of-the-art neural chatbots cannot produce satisfying responses for every turn in a dialog. A practical solution is to generate multiple response candidates for the same context, and then perform response ranking/selection to determine which candidate is the best. Previous work in response selection typically trains response rankers using synthetic data that is formed from existing dialogs by using a ground truth response as the single appropriate response and constructing inappropriate responses via random selection or using adversarial methods. In this work, we curated a dataset where responses from multiple response generators produced for the same dialog context are manually annotated as appropriate (positive) and inappropriate (negative). We argue that such training data better matches the actual use case examples, enabling the models to learn to rank responses effectively. With this new dataset, we conduct a systematic evaluation of state-of-the-art methods for response selection, and demonstrate that both strategies of using multiple positive candidates and using manually verified hard negative candidates can bring in significant performance improvement in comparison to using the adversarial training data, e.g., increase of 3% and 13% in Recall@1 score, respectively.

Though chatbots based on large neural models can often produce fluent responses in open domain conversations, one salient error type is contradiction or inconsistency with the preceding conversation turns. Previous work has treated contradiction detection in bot responses as a task similar to natural language inference, e.g., detect the contradiction between a pair of bot utterances. However, utterances in conversations may contain co-references or ellipsis, and using these utterances as is may not always be sufficient for identifying contradictions. This work aims to improve the contradiction detection via rewriting all bot utterances to restore co-references and ellipsis. We curated a new dataset for utterance rewriting and built a rewriting model on it. We empirically demonstrate that this model can produce satisfactory rewrites to make bot utterances more complete. Furthermore, using rewritten utterances improves contradiction detection performance significantly, e.g., the AUPR and joint accuracy scores (detecting contradiction along with evidence) increase by 6.5% and 4.5% (absolute increase), respectively.

Prefix-tuning, or more generally continuous prompt tuning, has become an essential paradigm of parameter-efficient transfer learning. Using a large pre-trained language model (PLM), prefix-tuning can obtain strong performance by training only a small portion of parameters. In this paper, we propose to understand and further develop prefix-tuning through the kernel lens. Specifically, we make an analogy between prefixes and inducing variables in kernel methods and hypothesize that prefixes serving as inducing variables would improve their overall mechanism. From the kernel estimator perspective, we suggest a new variant of prefix-tuning—inducer-tuning, which shares the exact mechanism as prefix-tuning while leveraging the residual form found in adapter-tuning. This mitigates the initialization issue in prefix-tuning. Through comprehensive empirical experiments on natural language understanding and generation tasks, we demonstrate that inducer-tuning can close the performance gap between prefix-tuning and fine-tuning.

Embodied Vision and Language Task Completion requires an embodied agent to interpret natural language instructions and egocentric visual observations to navigate through and interact with environments. In this work, we examine ALFRED, a challenging benchmark for embodied task completion, with the goal of gaining insight into how effectively models utilize language. We find evidence that sequence-to-sequence and transformer-based models trained on this benchmark are not sufficiently sensitive to changes in input language instructions. Next, we construct a new test split – ALFRED-L to test whether ALFRED models can generalize to task structures not seen during training that intuitively require the same types of language understanding required in ALFRED. Evaluation of existing models on ALFRED-L suggests that (a) models are overly reliant on the sequence in which objects are visited in typical ALFRED trajectories and fail to adapt to modifications of this sequence and (b) models trained with additional augmented trajectories are able to adapt relatively better to such changes in input language instructions.

Interactive robots navigating photo-realistic environments need to be trained to effectively leverage and handle the dynamic nature of dialogue in addition to the challenges underlying vision-and-language navigation (VLN). In this paper, we present VISITRON, a multi-modal Transformer-based navigator better suited to the interactive regime inherent to Cooperative Vision-and-Dialog Navigation (CVDN). VISITRON is trained to: i) identify and associate object-level concepts and semantics between the environment and dialogue history, ii) identify when to interact vs. navigate via imitation learning of a binary classification head. We perform extensive pre-training and fine-tuning ablations with VISITRON to gain empirical insights and improve performance on CVDN. VISITRON’s ability to identify when to interact leads to a natural generalization of the game-play mode introduced by Roman et al. (2020) for enabling the use of such models in different environments. VISITRON is competitive with models on the static CVDN leaderboard and attains state-of-the-art performance on the Success weighted by Path Length (SPL) metric.

Accurate automatic evaluation metrics for open-domain dialogs are in high demand. Existing model-based metrics for system response evaluation are trained on human annotated data, which is cumbersome to collect. In this work, we propose to use information that can be automatically extracted from the next user utterance, such as its sentiment or whether the user explicitly ends the conversation, as a proxy to measure the quality of the previous system response. This allows us to train on a massive set of dialogs with weak supervision, without requiring manual system turn quality annotations. Experiments show that our model is comparable to models trained on human annotated data. Furthermore, our model generalizes across both spoken and written open-domain dialog corpora collected from real and paid users.

The massive amount of trainable parameters in the pre-trained language models (PLMs) makes them hard to be deployed to multiple downstream tasks. To address this issue, parameter-efficient transfer learning methods have been proposed to tune only a few parameters during fine-tuning while freezing the rest. This paper looks at existing methods along this line through the kernel lens. Motivated by the connection between self-attention in transformer-based PLMs and kernel learning, we propose kernel-wise adapters, namely Kernel-mix, that utilize the kernel structure in self-attention to guide the assignment of the tunable parameters. These adapters use guidelines found in classical kernel learning and enable separate parameter tuning for each attention head. Our empirical results, over a diverse set of natural language generation and understanding tasks, show that our proposed adapters can attain or improve the strong performance of existing baselines.

Prompting inputs with natural language task descriptions has emerged as a popular mechanism to elicit reasonably accurate outputs from large-scale generative language models with little to no in-context supervision. This also helps gain insight into how well language models capture the semantics of a wide range of downstream tasks purely from self-supervised pre-training on massive corpora of unlabeled text. Such models have naturally also been exposed to a lot of undesirable content like racist and sexist language and there is only some work on awareness of models along these dimensions. In this paper, we define and comprehensively evaluate how well such language models capture the semantics of four tasks for bias: diagnosis, identification, extraction and rephrasing. We define three broad classes of task descriptions for these tasks: statement, question, and completion, with numerous lexical variants within each class. We study the efficacy of prompting for each task using these classes and the null task description across several decoding methods and few-shot examples. Our analyses indicate that language models are capable of performing these tasks to widely varying degrees across different bias dimensions, such as gender and political affiliation. We believe our work is an important step towards unbiased language models by quantifying the limits of current self-supervision objectives at accomplishing such sociologically challenging tasks.

As more users across the world are interacting with dialog agents in their daily life, there is a need for better speech understanding that calls for renewed attention to the dynamics between research in automatic speech recognition (ASR) and natural language understanding (NLU). We briefly review these research areas and lay out the current relationship between them. In light of the observations we make in this article, we argue that (1) NLU should be cognizant of the presence of ASR models being used upstream in a dialog system’s pipeline, (2) ASR should be able to learn from errors found in NLU, (3) there is a need for end-to-end data sets that provide semantic annotations on spoken input, (4) there should be stronger collaboration between ASR and NLU research communities.

Natural language guided embodied task completion is a challenging problem since it requires understanding natural language instructions, aligning them with egocentric visual observations, and choosing appropriate actions to execute in the environment to produce desired changes. We experiment with augmenting a transformer model for this task with modules that effectively utilize a wider field of view and learn to choose whether the next step requires a navigation or manipulation action. We observed that the proposed modules resulted in improved, and in fact state-of-the-art performance on an unseen validation set of a popular benchmark dataset, ALFRED. However, our best model selected using the unseen validation set underperforms on the unseen test split of ALFRED, indicating that performance on the unseen validation set may not in itself be a sufficient indicator of whether model improvements generalize to unseen test sets. We highlight this result as we believe it may be a wider phenomenon in machine learning tasks but primarily noticeable only in benchmarks that limit evaluations on test splits, and highlights the need to modify benchmark design to better account for variance in model performance.

Traditional goal-oriented dialogue systems rely on various components such as natural language understanding, dialogue state tracking, policy learning and response generation. Training each component requires annotations which are hard to obtain for every new domain, limiting scalability of such systems. Similarly, rule-based dialogue systems require extensive writing and maintenance of rules and do not scale either. End-to-End dialogue systems, on the other hand, do not require module-specific annotations but need a large amount of data for training. To overcome these problems, in this demo, we present Alexa Conversations, a new approach for building goal-oriented dialogue systems that is scalable, extensible as well as data efficient. The components of this system are trained in a data-driven manner, but instead of collecting annotated conversations for training, we generate them using a novel dialogue simulator based on a few seed dialogues and specifications of APIs and entities provided by the developer. Our approach provides out-of-the-box support for natural conversational phenomenon like entity sharing across turns or users changing their mind during conversation without requiring developers to provide any such dialogue flows. We exemplify our approach using a simple pizza ordering task and showcase its value in reducing the developer burden for creating a robust experience. Finally, we evaluate our system using a typical movie ticket booking task integrated with live APIs and show that the dialogue simulator is an essential component of the system that leads to over 50% improvement in turn-level action signature prediction accuracy.

In recent years, incorporating external knowledge for response generation in open-domain conversation systems has attracted great interest. To improve the relevancy of retrieved knowledge, we propose a neural entity linking (NEL) approach. Different from formal documents, such as news, conversational utterances are informal and multi-turn, which makes it more challenging to disambiguate the entities. Therefore, we present a context-aware named entity recognition model (NER) and entity resolution (ER) model to utilize dialogue context information. We conduct NEL experiments on three open-domain conversation datasets and validate that incorporating context information improves the performance of NER and ER models. The end-to-end NEL approach outperforms the baseline by 62.8% relatively in F1 metric. Furthermore, we verify that using external knowledge based on NEL benefits the neural response generation model.

Recent vision-language understanding approaches adopt a multi-modal transformer pre-training and finetuning paradigm. Prior work learns representations of text tokens and visual features with cross-attention mechanisms and captures the alignment solely based on indirect signals. In this work, we propose to enhance the alignment mechanism by incorporating image scene graph structures as the bridge between the two modalities, and learning with new contrastive objectives. In our preliminary study on the challenging compositional visual question answering task, we show the proposed approach achieves improved results, demonstrating potentials to enhance vision-language understanding.

Most prior work on task-oriented dialogue systems are restricted to limited coverage of domain APIs. However, users oftentimes have requests that are out of the scope of these APIs. This work focuses on responding to these beyond-API-coverage user turns by incorporating external, unstructured knowledge sources. Our approach works in a pipelined manner with knowledge-seeking turn detection, knowledge selection, and response generation in sequence. We introduce novel data augmentation methods for the first two steps and demonstrate that the use of information extracted from dialogue context improves the knowledge selection and end-to-end performances. Through experiments, we achieve state-of-the-art performance for both automatic and human evaluation metrics on the DSTC9 Track 1 benchmark dataset, validating the effectiveness of our contributions.

Dialogue State Tracking (DST) forms a core component of automated chatbot based systems designed for specific goals like hotel, taxi reservation, tourist information etc. With the increasing need to deploy such systems in new domains, solving the problem of zero/few-shot DST has become necessary. There has been a rising trend for learning to transfer knowledge from resource-rich domains to unknown domains with minimal need for additional data. In this work, we explore the merits of meta-learning algorithms for this transfer and hence, propose a meta-learner D-REPTILE specific to the DST problem. With extensive experimentation, we provide clear evidence of benefits over conventional approaches across different domains, methods, base models and datasets with significant (5-25%) improvement over the baseline in a low-data setting. Our proposed meta-learner is agnostic of the underlying model and hence any existing state-of-the-art DST system can improve its performance on unknown domains using our training strategy.

Incorporating external knowledge sources effectively in conversations is a longstanding problem in open-domain dialogue research. The existing literature on open-domain knowledge selection is limited and makes certain brittle assumptions on knowledge sources to simplify the overall task, such as the existence of a single relevant knowledge sentence per context. In this work, we evaluate the existing state of open-domain conversation knowledge selection, showing where the existing methodologies regarding data and evaluation are flawed. We then improve on them by proposing a new framework for collecting relevant knowledge, and create an augmented dataset based on the Wizard of Wikipedia (WOW) corpus, which we call WOW++. WOW++ averages 8 relevant knowledge sentences per dialogue context, embracing the inherent ambiguity of open-domain dialogue knowledge selection. We then benchmark various knowledge ranking algorithms on this augmented dataset with both intrinsic evaluation and extrinsic measures of response quality, showing that neural rerankers that use WOW++ can outperform rankers trained on standard datasets.

Inspired by recent work in meta-learning and generative teaching networks, we propose a framework called Generative Conversational Networks, in which conversational agents learn to generate their own labelled training data (given some seed data) and then train themselves from that data to perform a given task. We use reinforcement learning to optimize the data generation process where the reward signal is the agent’s performance on the task. The task can be any language-related task, from intent detection to full task-oriented conversations. In this work, we show that our approach is able to generalise from seed data and performs well in limited data and limited computation settings, with significant gains for intent detection and slot tagging across multiple datasets: ATIS, TOD, SNIPS, and Restaurants8k. We show an average improvement of 35% in intent detection and 21% in slot tagging over a baseline model trained from the seed data. We also conduct an analysis of the novelty of the generated data and provide generated examples for intent detection, slot tagging, and non-goal oriented conversations.

Smooth and effective communication requires the ability to perform latent or explicit commonsense inference. Prior commonsense reasoning benchmarks (such as SocialIQA and CommonsenseQA) mainly focus on the discriminative task of choosing the right answer from a set of candidates, and do not involve interactive language generation as in dialogue. Moreover, existing dialogue datasets do not explicitly focus on exhibiting commonsense as a facet. In this paper, we present an empirical study of commonsense in dialogue response generation. We first auto-extract commonsensical dialogues from existing dialogue datasets by leveraging ConceptNet, a commonsense knowledge graph. Furthermore, building on social contexts/situations in SocialIQA, we collect a new dialogue dataset with 25K dialogues aimed at exhibiting social commonsense in an interactive setting. We evaluate response generation models trained using these datasets and find that models trained on both extracted and our collected data produce responses that consistently exhibit more commonsense than baselines. Finally we propose an approach for automatic evaluation of commonsense that relies on features derived from ConceptNet and pre-trained language and dialog models, and show reasonable correlation with human evaluation of responses’ commonsense quality.

Natural Language Generation (NLG) for task-oriented dialogue systems focuses on communicating specific content accurately, fluently, and coherently. While these attributes are crucial for a successful dialogue, it is also desirable to simultaneously accomplish specific stylistic goals, such as response length, point-of-view, descriptiveness, sentiment, formality, and empathy. In this work, we focus on stylistic control and evaluation for schema-guided NLG, with joint goals of achieving both semantic and stylistic control. We experiment in detail with various controlled generation methods for large pretrained language models: specifically, conditional training, guided fine-tuning, and guided decoding. We discuss their advantages and limitations, and evaluate them with a broad range of automatic and human evaluation metrics. Our results show that while high style accuracy and semantic correctness are easier to achieve for more lexically-defined styles with conditional training, stylistic control is also achievable for more semantically complex styles using discriminator-based guided decoding methods. The results also suggest that methods that are more scalable (with less hyper-parameters tuning) and that disentangle context generation and stylistic variations are more effective at achieving semantic correctness and style accuracy.

Humans make appropriate responses not only based on previous dialogue utterances but also on implicit background knowledge such as common sense. Although neural response generation models seem to produce human-like responses, they are mostly end-to-end and not generating intermediate grounds between a dialogue history and responses. This work aims to study if and how we can train an RG model that talks with itself to generate implicit knowledge before making responses. We further investigate can such models identify when to generate implicit background knowledge and when it is not necessary. Experimental results show that compared with models that directly generate responses given a dialogue history, self-talk models produce better-quality responses according to human evaluation on grammaticality, coherence, and engagingness. And models that are trained to identify when to self-talk further improves the response quality. Analysis on generated implicit knowledge shows that models mostly use the knowledge appropriately in the responses.

Most prior work on task-oriented dialogue systems is restricted to supporting domain APIs. However, users may have requests that are out of the scope of these APIs. This work focuses on identifying such user requests. Existing methods for this task mainly rely on fine-tuning pre-trained models on large annotated data. We propose a novel method, REDE, based on adaptive representation learning and density estimation. REDE can be applied to zero-shot cases, and quickly learns a high-performing detector with only a few shots by updating less than 3K parameters. We demonstrate REDE’s competitive performance on DSTC9 data and our newly collected test set.

MultiWOZ 2.0 (Budzianowski et al., 2018) is a recently released multi-domain dialogue dataset spanning 7 distinct domains and containing over 10,000 dialogues. Though immensely useful and one of the largest resources of its kind to-date, MultiWOZ 2.0 has a few shortcomings. Firstly, there are substantial noise in the dialogue state annotations and dialogue utterances which negatively impact the performance of state-tracking models. Secondly, follow-up work (Lee et al., 2019) has augmented the original dataset with user dialogue acts. This leads to multiple co-existent versions of the same dataset with minor modifications. In this work we tackle the aforementioned issues by introducing MultiWOZ 2.1. To fix the noisy state annotations, we use crowdsourced workers to re-annotate state and utterances based on the original utterances in the dataset. This correction process results in changes to over 32% of state annotations across 40% of the dialogue turns. In addition, we fix 146 dialogue utterances by canonicalizing slot values in the utterances to the values in the dataset ontology. To address the second problem, we combined the contributions of the follow-up works into MultiWOZ 2.1. Hence, our dataset also includes user dialogue acts as well as multiple slot descriptions per dialogue state slot. We then benchmark a number of state-of-the-art dialogue state tracking models on the MultiWOZ 2.1 dataset and show the joint state tracking performance on the corrected state annotations. We are publicly releasing MultiWOZ 2.1 to the community, hoping that this dataset resource will allow for more effective models across various dialogue subproblems to be built in the future.

Neural network based approaches to data-to-text natural language generation (NLG) have gained popularity in recent years, with the goal of generating a natural language prompt that accurately realizes an input meaning representation. To facilitate the training of neural network models, researchers created large datasets of paired utterances and their meaning representations. However, the creation of such datasets is an arduous task and they mostly consist of simple meaning representations composed of slot and value tokens to be realized. These representations do not include any contextual information that an NLG system can use when trying to generalize, such as domain information and descriptions of slots and values. In this paper, we present the novel task of Schema-Guided Natural Language Generation (SG-NLG). Here, the goal is still to generate a natural language prompt, but in SG-NLG, the input MRs are paired with rich schemata providing contextual information. To generate a dataset for SG-NLG we re-purpose an existing dataset for another task: dialog state tracking, which includes a large and rich schema spanning multiple different attributes, including information about the domain, user intent, and slot descriptions. We train different state-of-the-art models for neural natural language generation on this dataset and show that in many cases, including rich schema information allows our models to produce higher quality outputs both in terms of semantics and diversity. We also conduct experiments comparing model performance on seen versus unseen domains, and present a human evaluation demonstrating high ratings for overall output quality.

Open-domain dialog systems aim to generate relevant, informative and engaging responses. In this paper, we propose using a dialog policy to plan the content and style of target, open domain responses in the form of an action plan, which includes knowledge sentences related to the dialog context, targeted dialog acts, topic information, etc. For training, the attributes within the action plan are obtained by automatically annotating the publicly released Topical-Chat dataset. We condition neural response generators on the action plan which is then realized as target utterances at the turn and sentence levels. We also investigate different dialog policy models to predict an action plan given the dialog context. Through automated and human evaluation, we measure the appropriateness of the generated responses and check if the generation models indeed learn to realize the given action plans. We demonstrate that a basic dialog policy that operates at the sentence level generates better responses in comparison to turn level generation as well as baseline models with no action plan. Additionally the basic dialog policy has the added benefit of controllability.

Natural language generators (NLGs) for task-oriented dialogue typically take a meaning representation (MR) as input, and are trained end-to-end with a corpus of MR/utterance pairs, where the MRs cover a specific set of dialogue acts and domain attributes. Creation of such datasets is labor intensive and time consuming. Therefore, dialogue systems for new domain ontologies would benefit from using data for pre-existing ontologies. Here we explore, for the first time, whether it is possible to train an NLG for a new larger ontology using existing training sets for the restaurant domain, where each set is based on a different ontology. We create a new, larger combined ontology, and then train an NLG to produce utterances covering it. For example, if one dataset has attributes for family friendly and rating information, and the other has attributes for decor and service, our aim is an NLG for the combined ontology that can produce utterances that realize values for family friendly, rating, decor and service. Initial experiments with a baseline neural sequence-to-sequence model show that this task is surprisingly challenging. We then develop a novel self-training method that identifies (errorful) model outputs, automatically constructs a corrected MR input to form a new (MR, utterance) training pair, and then repeatedly adds these new instances back into the training data. We then test the resulting model on a new test set. The result is a self-trained model whose performance is an absolute 75.4% improvement over the baseline model. We also report a human qualitative evaluation of the final model showing that it achieves high naturalness, semantic coherence and grammaticality.

Most prior work on task-oriented dialogue systems are restricted to a limited coverage of domain APIs, while users oftentimes have domain related requests that are not covered by the APIs. In this paper, we propose to expand coverage of task-oriented dialogue systems by incorporating external unstructured knowledge sources. We define three sub-tasks: knowledge-seeking turn detection, knowledge selection, and knowledge-grounded response generation, which can be modeled individually or jointly. We introduce an augmented version of MultiWOZ 2.1, which includes new out-of-API-coverage turns and responses grounded on external knowledge sources. We present baselines for each sub-task using both conventional and neural approaches. Our experimental results demonstrate the need for further research in this direction to enable more informative conversational systems.

Pretrained language models have excelled at many NLP tasks recently; however, their social intelligence is still unsatisfactory. To enable this, machines need to have a more general understanding of our complicated world and develop the ability to perform commonsense reasoning besides fitting the specific downstream tasks. External commonsense knowledge graphs (KGs), such as ConceptNet, provide rich information about words and their relationships. Thus, towards general commonsense learning, we propose two approaches to implicitly and explicitly infuse such KGs into pretrained language models. We demonstrate our proposed methods perform well on SocialIQA, a social commonsense reasoning task, in both limited and full training data regimes.

Dialogue state tracking (DST) is at the heart of task-oriented dialogue systems. However, the scarcity of labeled data is an obstacle to building accurate and robust state tracking systems that work across a variety of domains. Existing approaches generally require some dialogue data with state information and their ability to generalize to unknown domains is limited. In this paper, we propose using machine reading comprehension (RC) in state tracking from two perspectives: model architectures and datasets. We divide the slot types in dialogue state into categorical or extractive to borrow the advantages from both multiple-choice and span-based reading comprehension models. Our method achieves near the current state-of-the-art in joint goal accuracy on MultiWOZ 2.1 given full training data. More importantly, by leveraging machine reading comprehension datasets, our method outperforms the existing approaches by many a large margin in few-shot scenarios when the availability of in-domain data is limited. Lastly, even without any state tracking data, i.e., zero-shot scenario, our proposed approach achieves greater than 90% average slot accuracy in 12 out of 30 slots in MultiWOZ 2.1.

Task-oriented dialog systems increasingly rely on deep learning-based slot filling models, usually needing extensive labeled training data for target domains. Often, however, little to no target domain training data may be available, or the training and target domain schemas may be misaligned, as is common for web forms on similar websites. Prior zero-shot slot filling models use slot descriptions to learn concepts, but are not robust to misaligned schemas. We propose utilizing both the slot description and a small number of examples of slot values, which may be easily available, to learn semantic representations of slots which are transferable across domains and robust to misaligned schemas. Our approach outperforms state-of-the-art models on two multi-domain datasets, especially in the low-data setting.

Recent advances in neural sequence-to-sequence models have led to promising results for several language generation-based tasks, including dialogue response generation, summarization, and machine translation. However, these models are known to have several problems, especially in the context of chit-chat based dialogue systems: they tend to generate short and dull responses that are often too generic. Furthermore, these models do not ground conversational responses on knowledge and facts, resulting in turns that are not accurate, informative and engaging for the users. In this paper, we propose and experiment with a series of response generation models that aim to serve in the general scenario where in addition to the dialogue context, relevant unstructured external knowledge in the form of text is also assumed to be available for models to harness. Our proposed approach extends pointer-generator networks (See et al., 2017) by allowing the decoder to hierarchically attend and copy from external knowledge in addition to the dialogue context. We empirically show the effectiveness of the proposed model compared to several baselines including (Ghazvininejadet al., 2018; Zhang et al., 2018) through both automatic evaluation metrics and human evaluation on ConvAI2 dataset.

Understanding and conversing about dynamic scenes is one of the key capabilities of AI agents that navigate the environment and convey useful information to humans. Video question answering is a specific scenario of such AI-human interaction where an agent generates a natural language response to a question regarding the video of a dynamic scene. Incorporating features from multiple modalities, which often provide supplementary information, is one of the challenging aspects of video question answering. Furthermore, a question often concerns only a small segment of the video, hence encoding the entire video sequence using a recurrent neural network is not computationally efficient. Our proposed question-guided video representation module efficiently generates the token-level video summary guided by each word in the question. The learned representations are then fused with the question to generate the answer. Through empirical evaluation on the Audio Visual Scene-aware Dialog (AVSD) dataset, our proposed models in single-turn and multi-turn question answering achieve state-of-the-art performance on several automatic natural language generation evaluation metrics.

Dialog state tracking is used to estimate the current belief state of a dialog given all the preceding conversation. Machine reading comprehension, on the other hand, focuses on building systems that read passages of text and answer questions that require some understanding of passages. We formulate dialog state tracking as a reading comprehension task to answer the question what is the state of the current dialog? after reading conversational context. In contrast to traditional state tracking methods where the dialog state is often predicted as a distribution over a closed set of all the possible slot values within an ontology, our method uses a simple attention-based neural network to point to the slot values within the conversation. Experiments on MultiWOZ-2.0 cross-domain dialog dataset show that our simple system can obtain similar accuracies compared to the previous more complex methods. By exploiting recent advances in contextual word embeddings, adding a model that explicitly tracks whether a slot value should be carried over to the next turn, and combining our method with a traditional joint state tracking method that relies on closed set vocabulary, we can obtain a joint-goal accuracy of 47.33% on the standard test split, exceeding current state-of-the-art by 11.75%**.

Encoder-decoder based neural architectures serve as the basis of state-of-the-art approaches in end-to-end open domain dialog systems. Since most of such systems are trained with a maximum likelihood (MLE) objective they suffer from issues such as lack of generalizability and the generic response problem, i.e., a system response that can be an answer to a large number of user utterances, e.g., “Maybe, I don’t know.” Having explicit feedback on the relevance and interestingness of a system response at each turn can be a useful signal for mitigating such issues and improving system quality by selecting responses from different approaches. Towards this goal, we present a system that evaluates chatbot responses at each dialog turn for coherence and engagement. Our system provides explicit turn-level dialog quality feedback, which we show to be highly correlated with human evaluation. To show that incorporating this feedback in the neural response generation models improves dialog quality, we present two different and complementary mechanisms to incorporate explicit feedback into a neural response generation model: reranking and direct modification of the loss function during training. Our studies show that a response generation model that incorporates these combined feedback mechanisms produce more engaging and coherent responses in an open-domain spoken dialog setting, significantly improving the response quality using both automatic and human evaluation.

Current approaches to Natural Language Generation (NLG) for dialog mainly focus on domain-specific, task-oriented applications (e.g. restaurant booking) using limited ontologies (up to 20 slot types), usually without considering the previous conversation context. Furthermore, these approaches require large amounts of data for each domain, and do not benefit from examples that may be available for other domains. This work explores the feasibility of applying statistical NLG to scenarios requiring larger ontologies, such as multi-domain dialog applications or open-domain question answering (QA) based on knowledge graphs. We model NLG through an Encoder-Decoder framework using a large dataset of interactions between real-world users and a conversational agent for open-domain QA. First, we investigate the impact of increasing the number of slot types on the generation quality and experiment with different partitions of the QA data with progressively larger ontologies (up to 369 slot types). Second, we perform multi-task learning experiments between open-domain QA and task-oriented dialog, and benchmark our model on a popular NLG dataset. Moreover, we experiment with using the conversational context as an additional input to improve response generation quality. Our experiments show the feasibility of learning statistical NLG models for open-domain QA with larger ontologies.

In this work, we present a hybrid learning method for training task-oriented dialogue systems through online user interactions. Popular methods for learning task-oriented dialogues include applying reinforcement learning with user feedback on supervised pre-training models. Efficiency of such learning method may suffer from the mismatch of dialogue state distribution between offline training and online interactive learning stages. To address this challenge, we propose a hybrid imitation and reinforcement learning method, with which a dialogue agent can effectively learn from its interaction with users by learning from human teaching and feedback. We design a neural network based task-oriented dialogue agent that can be optimized end-to-end with the proposed learning method. Experimental results show that our end-to-end dialogue agent can learn effectively from the mistake it makes via imitation learning from user teaching. Applying reinforcement learning with user feedback after the imitation learning stage further improves the agent’s capability in successfully completing a task.

End-to-end neural models show great promise towards building conversational agents that are trained from data and on-line experience using supervised and reinforcement learning. However, these models require a large corpus of dialogues to learn effectively. For goal-oriented dialogues, such datasets are expensive to collect and annotate, since each task involves a separate schema and database of entities. Further, the Wizard-of-Oz approach commonly used for dialogue collection does not provide sufficient coverage of salient dialogue flows, which is critical for guaranteeing an acceptable task completion rate in consumer-facing conversational agents. In this paper, we study a recently proposed approach for building an agent for arbitrary tasks by combining dialogue self-play and crowd-sourcing to generate fully-annotated dialogues with diverse and natural utterances. We discuss the advantages of this approach for industry applications of conversational agents, wherein an agent can be rapidly bootstrapped to deploy in front of users and further optimized via interactive learning from actual users of the system.

This paper presents a novel approach for multi-task learning of language understanding (LU) and dialogue state tracking (DST) in task-oriented dialogue systems. Multi-task training enables the sharing of the neural network layers responsible for encoding the user utterance for both LU and DST and improves performance while reducing the number of network parameters. In our proposed framework, DST operates on a set of candidate values for each slot that has been mentioned so far. These candidate sets are generated using LU slot annotations for the current user utterance, dialogue acts corresponding to the preceding system utterance and the dialogue state estimated for the previous turn, enabling DST to handle slots with a large or unbounded set of possible values and deal with slot values not seen during training. Furthermore, to bridge the gap between training and inference, we investigate the use of scheduled sampling on LU output for the current user utterance as well as the DST output for the preceding turn.

Spoken Language Understanding (SLU) is a key component of goal oriented dialogue systems that would parse user utterances into semantic frame representations. Traditionally SLU does not utilize the dialogue history beyond the previous system turn and contextual ambiguities are resolved by the downstream components. In this paper, we explore novel approaches for modeling dialogue context in a recurrent neural network (RNN) based language understanding system. We propose the Sequential Dialogue Encoder Network, that allows encoding context from the dialogue history in chronological order. We compare the performance of our proposed architecture with two context models, one that uses just the previous turn context and another that encodes dialogue context in a memory network, but loses the order of utterances in the dialogue history. Experiments with a multi-domain dialogue dataset demonstrate that the proposed architecture results in reduced semantic frame error rates.

In the past decade, goal-oriented spoken dialogue systems have been the most prominent component in today's virtual personal assistants. The classic dialogue systems have rather complex and/or modular pipelines. The advance of deep learning technologies has recently risen the applications of neural models to dialogue modeling. However, how to successfully apply deep learning based approaches to a dialogue system is still challenging. Hence, this tutorial is designed to focus on an overview of the dialogue system development while describing most recent research for building dialogue systems and summarizing the challenges, in order to allow researchers to study the potential improvements of the state-of-the-art dialogue systems. The tutorial material is available at http://deepdialogue.miulab.tw.

With emerging conversational data, automated content analysis is needed for better data interpretation, so that it is accurately understood and can be effectively integrated and utilized in various applications. ICSI meeting corpus is a publicly released data set of multi-party meetings in an organization that has been released over a decade ago, and has been fostering meeting understanding research since then. The original data collection includes transcription of participant turns as well as meta-data annotations, such as disfluencies and dialog act tags. This paper presents an extended set of annotations for the ICSI meeting corpus with a goal of deeply understanding meeting conversations, where participant turns are annotated by actionable items that could be performed by an automated meeting assistant. In addition to the user utterances that contain an actionable item, annotations also include the arguments associated with the actionable item. The set of actionable items are determined by aligning human-human interactions to human-machine interactions, where a data annotation schema designed for a virtual personal assistant (human-machine genre) is adapted to the meetings domain (human-human genre). The data set is formed by annotating participants’ utterances in meetings with potential intents/actions considering their contexts. The set of actions target what could be accomplished by an automated meeting assistant, such as taking a note of action items that a participant commits to, or finding emails or topic related documents that were mentioned during the meeting. A total of 10 defined intents/actions are considered as actionable items in meetings. Turns that include actionable intents were annotated for 22 public ICSI meetings, that include a total of 21K utterances, segmented by speaker turns. Participants’ spoken turns, possible actions along with associated arguments and their vector representations as computed by convolutional deep structured semantic models are included in the data set for future research. We present a detailed statistical analysis of the data set and analyze the performance of applying convolutional deep structured semantic models for an actionable item detection task. The data is available at http://research.microsoft.com/projects/meetingunderstanding/.