Factual accuracy is an important property of neural abstractive summarization models, especially in fact-critical domains such as the clinical literature. In this work, we introduce a guided continued pre-training stage for encoder-decoder models that improves their understanding of the factual attributes of documents, which is followed by supervised fine-tuning on summarization. Our approach extends the pre-training recipe of BART to incorporate 3 additional objectives based on PICO spans, which capture the population, intervention, comparison, and outcomes related to a clinical study. Experiments on multi-document summarization in the clinical domain demonstrate that our approach is competitive with prior work, improving the quality and factuality of the summaries and achieving the best-published results in factual accuracy on the MSLR task.
The 1st Workshop on Data Contamination (CONDA 2024) focuses on all relevant aspects of data contamination in natural language processing, where data contamination is understood as situations where evaluation data is included in pre-training corpora used to train large scale models, compromising evaluation results. The workshop fostered a shared task to collect evidence on data contamination in current available datasets and models. The goal of the shared task and associated database is to assist the community in understanding the extent of the problem and to assist researchers in avoiding reporting evaluation results on known contaminated resources. The shared task provides a structured, centralized public database for the collection of contamination evidence, open to contributions from the community via GitHub pool requests. This first compilation paper is based on 566 reported entries over 91 contaminated sources from a total of 23 contributors. The details of the individual contamination events are available in the platform. The platform continues to be online, open to contributions from the community.
Table-to-text generation involves generating appropriate textual descriptions given structured tabular data. It has attracted increasing attention in recent years thanks to the popularity of neural network models and the availability of large-scale datasets. A common feature across existing methods is their treatment of the input as a string, i.e., by employing linearization techniques that do not always preserve information in the table, are verbose, and lack space efficiency. We propose to rethink data-to-text generation as a visual recognition task, removing the need for rendering the input in a string format. We present PixT3, a multimodal table-to-text model that overcomes the challenges of linearization and input size limitations encountered by existing models. PixT3 is trained with a new self-supervised learning objective to reinforce table structure awareness and is applicable to open-ended and controlled generation settings. Experiments on the ToTTo and Logic2Text benchmarks show that PixT3 is competitive and, in some settings, superior to generators that operate solely on text.
We introduce Latxa, a family of large language models for Basque ranging from 7 to 70 billion parameters. Latxa is based on Llama 2, which we continue pretraining on a new Basque corpus comprising 4.3M documents and 4.2B tokens. Addressing the scarcity of high-quality benchmarks for Basque, we further introduce 4 multiple choice evaluation datasets: EusProficiency, comprising 5,169 questions from official language proficiency exams; EusReading, comprising 352 reading comprehension questions; EusTrivia, comprising 1,715 trivia questions from 5 knowledge areas; and EusExams, comprising 16,046 questions from public examinations. In our extensive evaluation, Latxa outperforms all previous open models we compare to by a large margin. In addition, it is competitive with GPT-4 Turbo in language proficiency and understanding, despite lagging behind in reading comprehension and knowledge-intensive tasks. Both the Latxa family of models, as well as our new pretraining corpora and evaluation datasets, are publicly available under open licenses. Our suite enables reproducible research on methods to build LLMs for low-resource languages.
Cross-lingual transfer-learning is widely used in Event Extraction for low-resource languages and involves a Multilingual Language Model that is trained in a source language and applied to the target language. This paper studies whether the typological similarity between source and target languages impacts the performance of cross-lingual transfer, an under-explored topic. We first focus on Basque as the target language, which is an ideal target language because it is typologically different from surrounding languages. Our experiments on three Event Extraction tasks show that the shared linguistic characteristic between source and target languages does have an impact on transfer quality. Further analysis of 72 language pairs reveals that for tasks that involve token classification such as entity and event trigger identification, common writing script and morphological features produce higher quality cross-lingual transfer. In contrast, for tasks involving structural prediction like argument extraction, common word order is the most relevant feature. In addition, we show that when increasing the training size, not all the languages scale in the same way in the cross-lingual setting. To perform the experiments we introduce EusIE, an event extraction dataset for Basque, which follows the Multilingual Event Extraction dataset (MEE). The dataset and code are publicly available.
In this position paper we argue that the classical evaluation on Natural Language Processing (NLP) tasks using annotated benchmarks is in trouble. The worst kind of data contamination happens when a Large Language Model (LLM) is trained on the test split of a benchmark, and then evaluated in the same benchmark. The extent of the problem is unknown, as it is not straightforward to measure. Contamination causes an overestimation of the performance of a contaminated model in a target benchmark and associated task with respect to their non-contaminated counterparts. The consequences can be very harmful, with wrong scientific conclusions being published while other correct ones are discarded. This position paper defines different levels of data contamination and argues for a community effort, including the development of automatic and semi-automatic measures to detect when data from a benchmark was exposed to a model, and suggestions for flagging papers with conclusions that are compromised by data contamination.
Methods for adapting language models (LMs) to new tasks and domains have traditionally assumed white-box access to the model, and work by modifying its parameters. However, this is incompatible with a recent trend in the field, where the highest quality models are only available as black-boxes through inference APIs. Even when the model weights are available, the computational cost of fine-tuning large LMs can be prohibitive for most practitioners. In this work, we present a lightweight method for adapting large LMs to new domains and tasks, assuming no access to their weights or intermediate activations. Our approach fine-tunes a small white-box LM and combines it with the large black-box LM at the probability level through a small network, learned on a small validation set. We validate our approach by adapting a large LM (OPT-30B) to several domains and a downstream task (machine translation), observing improved performance in all cases, of up to 9%, while using a domain expert 23x smaller.
Language Models are the core for almost any Natural Language Processing system nowadays. One of their particularities is their contextualized representations, a game changer feature when a disambiguation between word senses is necessary. In this paper we aim to explore to what extent language models are capable of discerning among senses at inference time. We performed this analysis by prompting commonly used Languages Models such as BERT or RoBERTa to perform the task of Word Sense Disambiguation (WSD). We leverage the relation between word senses and domains, and cast WSD as a textual entailment problem, where the different hypothesis refer to the domains of the word senses. Our results show that this approach is indeed effective, close to supervised systems.
The current workflow for Information Extraction (IE) analysts involves the definition of the entities/relations of interest and a training corpus with annotated examples. In this demonstration we introduce a new workflow where the analyst directly verbalizes the entities/relations, which are then used by a Textual Entailment model to perform zero-shot IE. We present the design and implementation of a toolkit with a user interface, as well as experiments on four IE tasks that show that the system achieves very good performance at zero-shot learning using only 5–15 minutes per type of a user’s effort. Our demonstration system is open-sourced at https://github.com/BBN-E/ZS4IE. A demonstration video is available at https://vimeo.com/676138340.
Round-trip Machine Translation (MT) is a popular choice for paraphrase generation, which leverages readily available parallel corpora for supervision. In this paper, we formalize the implicit similarity function induced by this approach, and show that it is susceptible to non-paraphrase pairs sharing a single ambiguous translation. Based on these insights, we design an alternative similarity metric that mitigates this issue by requiring the entire translation distribution to match, and implement a relaxation of it through the Information Bottleneck method. Our approach incorporates an adversarial term into MT training in order to learn representations that encode as much information about the reference translation as possible, while keeping as little information about the input as possible. Paraphrases can be generated by decoding back to the source from this representation, without having to generate pivot translations. In addition to being more principled and efficient than round-trip MT, our approach offers an adjustable parameter to control the fidelity-diversity trade-off, and obtains better results in our experiments.
Recent work has shown that NLP tasks such as Relation Extraction (RE) can be recasted as a Textual Entailment tasks using verbalizations, with strong performance in zero-shot and few-shot settings thanks to pre-trained entailment models. The fact that relations in current RE datasets are easily verbalized casts doubts on whether entailment would be effective in more complex tasks. In this work we show that entailment is also effective in Event Argument Extraction (EAE), reducing the need of manual annotation to 50% and 20% in ACE and WikiEvents, respectively, while achieving the same performance as with full training. More importantly, we show that recasting EAE as entailment alleviates the dependency on schemas, which has been a roadblock for transferring annotations between domains. Thanks to entailment, the multi-source transfer between ACE and WikiEvents further reduces annotation down to 10% and 5% (respectively) of the full training without transfer. Our analysis shows that key to good results is the use of several entailment datasets to pre-train the entailment model. Similar to previous approaches, our method requires a small amount of effort for manual verbalization: only less than 15 minutes per event argument types is needed; comparable results can be achieved from users of different level of expertise.
Formal verse poetry imposes strict constraints on the meter and rhyme scheme of poems. Most prior work on generating this type of poetry uses existing poems for supervision, which are difficult to obtain for most languages and poetic forms. In this work, we propose an unsupervised approach to generate poems that follow any given meter and rhyme scheme, without requiring any poetic text for training. Our method works by splitting a regular, non-poetic corpus into phrases, prepending control codes that describe the length and end rhyme of each phrase, and training a transformer language model in the augmented corpus. The transformer learns to link the structure descriptor with the control codes to the number of lines, their length and their end rhyme. During inference, we build control codes for the desired meter and rhyme scheme, and condition our language model on them to generate formal verse poetry. Experiments in Spanish and Basque show that our approach is able to generate valid poems, which are often comparable in quality to those written by humans.
Recent research on cross-lingual word embeddings has been dominated by unsupervised mapping approaches that align monolingual embeddings. Such methods critically rely on those embeddings having a similar structure, but it was recently shown that the separate training in different languages causes departures from this assumption. In this paper, we propose an alternative approach that does not have this limitation, while requiring a weak seed dictionary (e.g., a list of identical words) as the only form of supervision. Rather than aligning two fixed embedding spaces, our method works by fixing the target language embeddings, and learning a new set of embeddings for the source language that are aligned with them. To that end, we use an extension of skip-gram that leverages translated context words as anchor points, and incorporates self-learning and iterative restarts to reduce the dependency on the initial dictionary. Our approach outperforms conventional mapping methods on bilingual lexicon induction, and obtains competitive results in the downstream XNLI task.
Relation extraction systems require large amounts of labeled examples which are costly to annotate. In this work we reformulate relation extraction as an entailment task, with simple, hand-made, verbalizations of relations produced in less than 15 min per relation. The system relies on a pretrained textual entailment engine which is run as-is (no training examples, zero-shot) or further fine-tuned on labeled examples (few-shot or fully trained). In our experiments on TACRED we attain 63% F1 zero-shot, 69% with 16 examples per relation (17% points better than the best supervised system on the same conditions), and only 4 points short to the state-of-the-art (which uses 20 times more training data). We also show that the performance can be improved significantly with larger entailment models, up to 12 points in zero-shot, allowing to report the best results to date on TACRED when fully trained. The analysis shows that our few-shot systems are specially effective when discriminating between relations, and that the performance difference in low data regimes comes mainly from identifying no-relation cases.
The interaction of conversational systems with users poses an exciting opportunity for improving them after deployment, but little evidence has been provided of its feasibility. In most applications, users are not able to provide the correct answer to the system, but they are able to provide binary (correct, incorrect) feedback. In this paper we propose feedback-weighted learning based on importance sampling to improve upon an initial supervised system using binary user feedback. We perform simulated experiments on document classification (for development) and Conversational Question Answering datasets like QuAC and DoQA, where binary user feedback is derived from gold annotations. The results show that our method is able to improve over the initial supervised system, getting close to a fully-supervised system that has access to the same labeled examples in in-domain experiments (QuAC), and even matching in out-of-domain experiments (DoQA). Our work opens the prospect to exploit interactions with real users and improve conversational systems after deployment.
Conversational Question Answering (CQA) systems meet user information needs by having conversations with them, where answers to the questions are retrieved from text. There exist a variety of datasets for English, with tens of thousands of training examples, and pre-trained language models have allowed to obtain impressive results. The goal of our research is to test the performance of CQA systems under low-resource conditions which are common for most non-English languages: small amounts of native annotations and other limitations linked to low resource languages, like lack of crowdworkers or smaller wikipedias. We focus on the Basque language, and present the first non-English CQA dataset and results. Our experiments show that it is possible to obtain good results with low amounts of native data thanks to cross-lingual transfer, with quality comparable to those obtained for English. We also discovered that dialogue history models are not directly transferable to another language, calling for further research. The dataset is publicly available.
Word embeddings and pre-trained language models allow to build rich representations of text and have enabled improvements across most NLP tasks. Unfortunately they are very expensive to train, and many small companies and research groups tend to use models that have been pre-trained and made available by third parties, rather than building their own. This is suboptimal as, for many languages, the models have been trained on smaller (or lower quality) corpora. In addition, monolingual pre-trained models for non-English languages are not always available. At best, models for those languages are included in multilingual versions, where each language shares the quota of substrings and parameters with the rest of the languages. This is particularly true for smaller languages such as Basque. In this paper we show that a number of monolingual models (FastText word embeddings, FLAIR and BERT language models) trained with larger Basque corpora produce much better results than publicly available versions in downstream NLP tasks, including topic classification, sentiment classification, PoS tagging and NER. This work sets a new state-of-the-art in those tasks for Basque. All benchmarks and models used in this work are publicly available.
In this paper, we introduce a novel methodology to efficiently construct a corpus for question answering over structured data. For this, we introduce an intermediate representation that is based on the logical query plan in a database, called Operation Trees (OT). This representation allows us to invert the annotation process without loosing flexibility in the types of queries that we generate. Furthermore, it allows for fine-grained alignment of the tokens to the operations. Thus, we randomly generate OTs from a context free grammar and annotators just have to write the appropriate question and assign the tokens. We compare our corpus OTTA (Operation Trees and Token Assignment), a large semantic parsing corpus for evaluating natural language interfaces to databases, to Spider and LC-QuaD 2.0 and show that our methodology more than triples the annotation speed while maintaining the complexity of the queries. Finally, we train a state-of-the-art semantic parsing model on our data and show that our dataset is a challenging dataset and that the token alignment can be leveraged to significantly increase the performance.
The goal of this work is to build conversational Question Answering (QA) interfaces for the large body of domain-specific information available in FAQ sites. We present DoQA, a dataset with 2,437 dialogues and 10,917 QA pairs. The dialogues are collected from three Stack Exchange sites using the Wizard of Oz method with crowdsourcing. Compared to previous work, DoQA comprises well-defined information needs, leading to more coherent and natural conversations with less factoid questions and is multi-domain. In addition, we introduce a more realistic information retrieval (IR) scenario where the system needs to find the answer in any of the FAQ documents. The results of an existing, strong, system show that, thanks to transfer learning from a Wikipedia QA dataset and fine tuning on a single FAQ domain, it is possible to build high quality conversational QA systems for FAQs without in-domain training data. The good results carry over into the more challenging IR scenario. In both cases, there is still ample room for improvement, as indicated by the higher human upperbound.
We review motivations, definition, approaches, and methodology for unsupervised cross-lingual learning and call for a more rigorous position in each of them. An existing rationale for such research is based on the lack of parallel data for many of the world’s languages. However, we argue that a scenario without any parallel data and abundant monolingual data is unrealistic in practice. We also discuss different training signals that have been used in previous work, which depart from the pure unsupervised setting. We then describe common methodological issues in tuning and evaluation of unsupervised cross-lingual models and present best practices. Finally, we provide a unified outlook for different types of research in this area (i.e., cross-lingual word embeddings, deep multilingual pretraining, and unsupervised machine translation) and argue for comparable evaluation of these models.
Existing models of multilingual sentence embeddings require large parallel data resources which are not available for low-resource languages. We propose a novel unsupervised method to derive multilingual sentence embeddings relying only on monolingual data. We first produce a synthetic parallel corpus using unsupervised machine translation, and use it to fine-tune a pretrained cross-lingual masked language model (XLM) to derive the multilingual sentence representations. The quality of the representations is evaluated on two parallel corpus mining tasks with improvements of up to 22 F1 points over vanilla XLM. In addition, we observe that a single synthetic bilingual corpus is able to improve results for other language pairs.
We present a Question Answering (QA) system that won one of the tasks of the Kaggle CORD-19 Challenge, according to the qualitative evaluation of experts. The system is a combination of an Information Retrieval module and a reading comprehension module that finds the answers in the retrieved passages. In this paper we present a quantitative and qualitative analysis of the system. The quantitative evaluation using manually annotated datasets contradicted some of our design choices, e.g. the fact that using QuAC for fine-tuning provided better answers over just using SQuAD. We analyzed this mismatch with an additional A/B test which showed that the system using QuAC was indeed preferred by users, confirming our intuition. Our analysis puts in question the suitability of automatic metrics and its correlation to user preferences. We also show that automatic metrics are highly dependent on the characteristics of the gold standard, such as the average length of the answers.
The lack of time efficient and reliable evalu-ation methods is hampering the development of conversational dialogue systems (chat bots). Evaluations that require humans to converse with chat bots are time and cost intensive, put high cognitive demands on the human judges, and tend to yield low quality results. In this work, we introduce Spot The Bot, a cost-efficient and robust evaluation framework that replaces human-bot conversations with conversations between bots. Human judges then only annotate for each entity in a conversation whether they think it is human or not (assuming there are humans participants in these conversations). These annotations then allow us to rank chat bots regarding their ability to mimic conversational behaviour of humans. Since we expect that all bots are eventually recognized as such, we incorporate a metric that measures which chat bot is able to uphold human-like be-havior the longest, i.e.Survival Analysis. This metric has the ability to correlate a bot’s performance to certain of its characteristics (e.g.fluency or sensibleness), yielding interpretable results. The comparably low cost of our frame-work allows for frequent evaluations of chatbots during their evaluation cycle. We empirically validate our claims by applying Spot The Bot to three domains, evaluating several state-of-the-art chat bots, and drawing comparisonsto related work. The framework is released asa ready-to-use tool.
Both human and machine translation play a central role in cross-lingual transfer learning: many multilingual datasets have been created through professional translation services, and using machine translation to translate either the test set or the training set is a widely used transfer technique. In this paper, we show that such translation process can introduce subtle artifacts that have a notable impact in existing cross-lingual models. For instance, in natural language inference, translating the premise and the hypothesis independently can reduce the lexical overlap between them, which current models are highly sensitive to. We show that some previous findings in cross-lingual transfer learning need to be reconsidered in the light of this phenomenon. Based on the gained insights, we also improve the state-of-the-art in XNLI for the translate-test and zero-shot approaches by 4.3 and 2.8 points, respectively.
While machine translation has traditionally relied on large amounts of parallel corpora, a recent research line has managed to train both Neural Machine Translation (NMT) and Statistical Machine Translation (SMT) systems using monolingual corpora only. In this paper, we identify and address several deficiencies of existing unsupervised SMT approaches by exploiting subword information, developing a theoretically well founded unsupervised tuning method, and incorporating a joint refinement procedure. Moreover, we use our improved SMT system to initialize a dual NMT model, which is further fine-tuned through on-the-fly back-translation. Together, we obtain large improvements over the previous state-of-the-art in unsupervised machine translation. For instance, we get 22.5 BLEU points in English-to-German WMT 2014, 5.5 points more than the previous best unsupervised system, and 0.5 points more than the (supervised) shared task winner back in 2014.
Recent research in cross-lingual word embeddings has almost exclusively focused on offline methods, which independently train word embeddings in different languages and map them to a shared space through linear transformations. While several authors have questioned the underlying isomorphism assumption, which states that word embeddings in different languages have approximately the same structure, it is not clear whether this is an inherent limitation of mapping approaches or a more general issue when learning cross-lingual embeddings. So as to answer this question, we experiment with parallel corpora, which allows us to compare offline mapping to an extension of skip-gram that jointly learns both embedding spaces. We observe that, under these ideal conditions, joint learning yields to more isomorphic embeddings, is less sensitive to hubness, and obtains stronger results in bilingual lexicon induction. We thus conclude that current mapping methods do have strong limitations, calling for further research to jointly learn cross-lingual embeddings with a weaker cross-lingual signal.
A recent research line has obtained strong results on bilingual lexicon induction by aligning independently trained word embeddings in two languages and using the resulting cross-lingual embeddings to induce word translation pairs through nearest neighbor or related retrieval methods. In this paper, we propose an alternative approach to this problem that builds on the recent work on unsupervised machine translation. This way, instead of directly inducing a bilingual lexicon from cross-lingual embeddings, we use them to build a phrase-table, combine it with a language model, and use the resulting machine translation system to generate a synthetic parallel corpus, from which we extract the bilingual lexicon using statistical word alignment techniques. As such, our method can work with any word embedding and cross-lingual mapping technique, and it does not require any additional resource besides the monolingual corpus used to train the embeddings. When evaluated on the exact same cross-lingual embeddings, our proposed method obtains an average improvement of 6 accuracy points over nearest neighbor and 4 points over CSLS retrieval, establishing a new state-of-the-art in the standard MUSE dataset.
Word embeddings typically represent different meanings of a word in a single conflated vector. Empirical analysis of embeddings of ambiguous words is currently limited by the small size of manually annotated resources and by the fact that word senses are treated as unrelated individual concepts. We present a large dataset based on manual Wikipedia annotations and word senses, where word senses from different words are related by semantic classes. This is the basis for novel diagnostic tests for an embedding’s content: we probe word embeddings for semantic classes and analyze the embedding space by classifying embeddings into semantic classes. Our main findings are: (i) Information about a sense is generally represented well in a single-vector embedding – if the sense is frequent. (ii) A classifier can accurately predict whether a word is single-sense or multi-sense, based only on its embedding. (iii) Although rare senses are not well represented in single-vector embeddings, this does not have negative impact on an NLP application whose performance depends on frequent senses.
Named Entity Disambiguation algorithms typically learn a single model for all target entities. In this paper we present a word expert model and train separate deep learning models for each target entity string, yielding 500K classification tasks. This gives us the opportunity to benchmark popular text representation alternatives on this massive dataset. In order to face scarce training data we propose a simple data-augmentation technique and transfer-learning. We show that bag-of-word-embeddings are better than LSTMs for tasks with scarce training data, while the situation is reversed when having larger amounts. Transferring a LSTM which is learned on all datasets is the most effective context representation option for the word experts in all frequency bands. The experiments show that our system trained on out-of-domain Wikipedia data surpass comparable NED systems which have been trained on in-domain training data.
Following the recent success of word embeddings, it has been argued that there is no such thing as an ideal representation for words, as different models tend to capture divergent and often mutually incompatible aspects like semantics/syntax and similarity/relatedness. In this paper, we show that each embedding model captures more information than directly apparent. A linear transformation that adjusts the similarity order of the model without any external resource can tailor it to achieve better results in those aspects, providing a new perspective on how embeddings encode divergent linguistic information. In addition, we explore the relation between intrinsic and extrinsic evaluation, as the effect of our transformations in downstream tasks is higher for unsupervised systems than for supervised ones.
Recent work has managed to learn cross-lingual word embeddings without parallel data by mapping monolingual embeddings to a shared space through adversarial training. However, their evaluation has focused on favorable conditions, using comparable corpora or closely-related languages, and we show that they often fail in more realistic scenarios. This work proposes an alternative approach based on a fully unsupervised initialization that explicitly exploits the structural similarity of the embeddings, and a robust self-learning algorithm that iteratively improves this solution. Our method succeeds in all tested scenarios and obtains the best published results in standard datasets, even surpassing previous supervised systems. Our implementation is released as an open source project at https://github.com/artetxem/vecmap.
UKB is an open source collection of programs for performing, among other tasks, Knowledge-Based Word Sense Disambiguation (WSD). Since it was released in 2009 it has been often used out-of-the-box in sub-optimal settings. We show that nine years later it is the state-of-the-art on knowledge-based WSD. This case shows the pitfalls of releasing open source NLP software without optimal default settings and precise instructions for reproducibility.
While modern machine translation has relied on large parallel corpora, a recent line of work has managed to train Neural Machine Translation (NMT) systems from monolingual corpora only (Artetxe et al., 2018c; Lample et al., 2018). Despite the potential of this approach for low-resource settings, existing systems are far behind their supervised counterparts, limiting their practical interest. In this paper, we propose an alternative approach based on phrase-based Statistical Machine Translation (SMT) that significantly closes the gap with supervised systems. Our method profits from the modular architecture of SMT: we first induce a phrase table from monolingual corpora through cross-lingual embedding mappings, combine it with an n-gram language model, and fine-tune hyperparameters through an unsupervised MERT variant. In addition, iterative backtranslation improves results further, yielding, for instance, 14.08 and 26.22 BLEU points in WMT 2014 English-German and English-French, respectively, an improvement of more than 7-10 BLEU points over previous unsupervised systems, and closing the gap with supervised SMT (Moses trained on Europarl) down to 2-5 BLEU points. Our implementation is available at https://github.com/artetxem/monoses.
Semantic Textual Similarity (STS) measures the meaning similarity of sentences. Applications include machine translation (MT), summarization, generation, question answering (QA), short answer grading, semantic search, dialog and conversational systems. The STS shared task is a venue for assessing the current state-of-the-art. The 2017 task focuses on multilingual and cross-lingual pairs with one sub-track exploring MT quality estimation (MTQE) data. The task obtained strong participation from 31 teams, with 17 participating in all language tracks. We summarize performance and review a selection of well performing methods. Analysis highlights common errors, providing insight into the limitations of existing models. To support ongoing work on semantic representations, the STS Benchmark is introduced as a new shared training and evaluation set carefully selected from the corpus of English STS shared task data (2012-2017).
Most methods to learn bilingual word embeddings rely on large parallel corpora, which is difficult to obtain for most language pairs. This has motivated an active research line to relax this requirement, with methods that use document-aligned corpora or bilingual dictionaries of a few thousand words instead. In this work, we further reduce the need of bilingual resources using a very simple self-learning approach that can be combined with any dictionary-based mapping technique. Our method exploits the structural similarity of embedding spaces, and works with as little bilingual evidence as a 25 word dictionary or even an automatically generated list of numerals, obtaining results comparable to those of systems that use richer resources.
This paper presents the evaluation of the translation quality and Cross-Lingual Information Retrieval (CLIR) performance when using session information as the context of queries. The hypothesis is that previous queries provide context that helps to solve ambiguous translations in the current query. We tested several strategies on the TREC 2010 Session track dataset, which includes query reformulations grouped by generalization, specification, and drifting types. We study the Basque to English direction, evaluating both the translation quality and CLIR performance, with positive results in both cases. The results show that the quality of translation improved, reducing error rate by 12% (HTER) when using session information, which improved CLIR results 5% (nDCG). We also provide an analysis of the improvements across the three kinds of sessions: generalization, specification, and drifting. Translation quality improved in all three types (generalization, specification, and drifting), and CLIR improved for generalization and specification sessions, preserving the performance in drifting sessions.
Named Entity Disambiguation (NED) is the task of linking a named-entity mention to an instance in a knowledge-base, typically Wikipedia-derived resources like DBpedia. This task is closely related to word-sense disambiguation (WSD), where the mention of an open-class word is linked to a concept in a knowledge-base, typically WordNet. This paper analyzes the relation between two annotated datasets on NED and WSD, highlighting the commonalities and differences. We detail the methods to construct a NED system following the WSD word-expert approach, where we need a dictionary and one classifier is built for each target entity mention string. Constructing a dictionary for NED proved challenging, and although similarity and ambiguity are higher for NED, the results are also higher due to the larger number of training data, and the more crisp and skewed meaning differences.
Word Sense Disambiguation (WSD) systems tend to have a strong bias towards assigning the Most Frequent Sense (MFS), which results in high performance on the MFS but in a very low performance on the less frequent senses. We addressed the MFS bias in WSD systems by combining the output from a WSD system with a set of mostly static features to create a MFS classifier to decide when to and not to choose the MFS. The output from this MFS classifier, which is based on the Random Forest algorithm, is then used to modify the output from the original WSD system. We applied our classifier to one of the state-of-the-art supervised WSD systems, i.e. IMS, and to of the best state-of-the-art unsupervised WSD systems, i.e. UKB. Our main finding is that we are able to improve the system output in terms of choosing between the MFS and the less frequent senses. When we apply the MFS classifier to fine-grained WSD, we observe an improvement on the less frequent sense cases, whereas we maintain the overall recall.
Although it is commonly assumed that word sense disambiguation (WSD) should help to improve lexical choice and improve the quality of machine translation systems, how to successfully integrate word senses into such systems remains an unanswered question. Some successful approaches have involved reformulating either WSD or the word senses it produces, but work on using traditional word senses to improve machine translation have met with limited success. In this paper, we build upon previous work that experimented on including word senses as contextual features in maxent-based translation models. Training on a large, open-domain corpus (Europarl), we demonstrate that this aproach yields significant improvements in machine translation from English to Portuguese.
This work presents parallel corpora automatically annotated with several NLP tools, including lemma and part-of-speech tagging, named-entity recognition and classification, named-entity disambiguation, word-sense disambiguation, and coreference. The corpora comprise both the well-known Europarl corpus and a domain-specific question-answer troubleshooting corpus on the IT domain. English is common in all parallel corpora, with translations in five languages, namely, Basque, Bulgarian, Czech, Portuguese and Spanish. We describe the annotated corpora and the tools used for annotation, as well as annotation statistics for each language. These new resources are freely available and will help research on semantic processing for machine translation and cross-lingual transfer.
Selecting appropriate translations for source words with multiple meanings still remains a challenge for statistical machine translation (SMT). One reason for this is that most SMT systems are not good at detecting the proper sense for a polysemic word when it appears in different contexts. In this paper, we adopt a supersense tagging method to annotate source words with coarse-grained ontological concepts. In order to enable the system to choose an appropriate translation for a word or phrase according to the annotated supersense of the word or phrase, we propose two translation models with supersense knowledge: a maximum entropy based model and a supersense embedding model. The effectiveness of our proposed models is validated on a large-scale English-to-Spanish translation task. Results indicate that our method can significantly improve translation quality via correctly conveying the meaning of the source language to the target language.
Digitised Cultural Heritage (CH) items usually have short descriptions and lack rich contextual information. Wikipedia articles, on the contrary, include in-depth descriptions and links to related articles, which motivate the enrichment of CH items with information from Wikipedia. In this paper we explore the feasibility of finding matching articles in Wikipedia for a given Cultural Heritage item. We manually annotated a random sample of items from Europeana, and performed a qualitative and quantitative study of the issues and problems that arise, showing that each kind of CH item is different and needs a nuanced definition of what ``matching article'' means. In addition, we test a well-known wikification (aka entity linking) algorithm on the task. Our results indicate that a substantial number of items can be effectively linked to their corresponding Wikipedia article.
Graph-based similarity over WordNet has been previously shown to perform very well on word similarity. This paper presents a study of the performance of such a graph-based algorithm when using different relations and versions of Wordnet. The graph algorithm is based on Personalized PageRank, a random-walk based algorithm which computes the probability of a random-walk initiated in the target word to reach any synset following the relations in WordNet (Haveliwala, 2002). Similarity is computed as the cosine of the probability distributions for each word over WordNet. The best combination of relations includes all relations in WordNet 3.0, included disambiguated glosses, and automatically disambiguated topic signatures called KnowNets. All relations are part of the official release of WordNet, except KnowNets, which have been derived automatically. The results over the WordSim 353 dataset show that using the adequate relations the performance improves over previously published WordNet-based results on the WordSim353 dataset (Finkelstein et al., 2002). The similarity software and some graphs used in this paper are publicly available at http://ixa2.si.ehu.es/ukb.
This paper presents the results of a graph-based method for performing knowledge-based Word Sense Disambiguation (WSD). The technique exploits the structural properties of the graph underlying the chosen knowledge base. The method is general, in the sense that it is not tied to any particular knowledge base, but in this work we have applied it to the Multilingual Central Repository (MCR). The evaluation has been performed on the Senseval-3 all-words task. The main contributions of the paper are twofold: (1) We have evaluated the separate and combined performance of each type of relation in the MCR, and thus indirectly validated the contents of the MCR and their potential for WSD. (2) We obtain state-of-the-art results, and in fact yield the best results that can be obtained using publicly available data.
We outline work performed within the framework of a current EC project. The goal is to construct a language-independent information system for a specific domain (environment/ecology/biodiversity) anchored in a language-independent ontology that is linked to wordnets in seven languages. For each language, information extraction and identification of lexicalized concepts with ontological entries is carried out by text miners (Kybots). The mapping of language-specific lexemes to the ontology allows for crosslinguistic identification and translation of equivalent terms. The infrastructure developed within this project enables long-range knowledge sharing and transfer across many languages and cultures, addressing the need for global and uniform transition of knowledge beyond the specific domains addressed here.
In this paper we describe the methodology and the first steps for the creation of WNTERM (from WordNet and Terminology), a specialized lexicon produced from the merger of the EuroWordNet-based Multilingual Central Repository (MCR) and the Basic Encyclopaedic Dictionary of Science and Technology (BDST). As an example, the ecology domain has been used. The final result is a multilingual (Basque and English) light-weight domain ontology, including taxonomic and other semantic relations among its concepts, which is tightly connected to other wordnets.
This paper presents a methodology for adding a layer of semantic annotation to a syntactically annotated corpus of Basque (EPEC), in terms of semantic roles. The proposal we make here is the combination of three resources: the model used in the PropBank project (Palmer et al., 2005), an in-house database with syntactic/semantic subcategorization frames for Basque verbs (Aldezabal, 2004) and the Basque dependency treebank (Aduriz et al., 2003). In order to validate the methodology and to confirm whether the PropBank model is suitable for Basque and our treebank design, we have built lexical entries and labelled all argument and adjuncts occurring in our treebank for 3 Basque verbs. The result of this study has been very positive, and has produced a methodology adapted to the characteristics of the language and the Basque dependency treebank. Another goal of this study was to study whether semi-automatic tagging was possible. The idea is to present the human taggers a pre-tagged version of the corpus. We have seen that many arguments could be automatically tagged with high precision, given only the verbal entries for the verbs and a handful of examples.
This paper describes the methodology adopted to jointly develop the Basque WordNet and a hand annotated corpora (the Basque Semcor). This joint development allows for better motivated sense distinctions, and a tighter coupling between both resources. The methodology involves edition, tagging and refereeing tasks. We are currently half way through the nominal part of the 300.000 word corpus (roughly equivalent to a 500.000 word corpus for English). We present a detailed description of the task, including the main criteria for difficult cases in the edition of the senses and the tagging of the corpus, with special mention to multiword entries. Finally we give a detailed picture of the current figures, as well as an analysis of the agreement rates.