Conversational humor is the key to capturing dialogue semantics and dialogue comprehension, which is usually generated in multiple modalities, such as linguistic rhetoric (textual modality), exaggerated facial expressions or movements (visual modality), and quirky intonation (acoustic modality). However, existing multimodal corpora for conversation humor are coarse-grained, and the modality is insufficient to support the conversational humor recognition task. This paper designed an annotation scheme for multimodal humor datasets, and constructed a corpus based on a Chinese sitcom for conversational humor recognition, named MUCH. The MUCH corpus consists of 34,804 utterances in total, and 7,079 of them are humorous. We employed both unimodal and multimodal methods to test our MUCH corpus. Experimental results showed that the multimodal approach could achieve 75.94% in terms of F1-score and surpassed the performance of most unimodal methods, which demonstrated that the MUCH corpus was effective for multimodal humor recognition tasks.

The goal of Emotion Cause Pair Extraction (ECPE) is to explore the causes of emotion changes and what causes a certain emotion. This paper proposes a three-step learning approach for the task of Textual Emotion-Cause Pair Extraction in Conversations in SemEval-2024 Task 3, named ECSP. We firstly perform data preprocessing operations on the original dataset to construct negative samples. Secondly, we use a pre-trained model to construct token sequence representations with contextual information to obtain emotion prediction. Thirdly, we regard the textual emotion-cause pair extraction task as a machine reading comprehension task, and fine-tune two pre-trained models, RoBERTa and SpanBERT. Our results have achieved good results in the official rankings, ranking 3rd under the strict match with the Strict F1-score of 15.18%, which further shows that our system has a robust performance.

Recent work has demonstrated that using parameter efficient tuning techniques such as prefix tuning (or P-tuning) on pretrained language models can yield performance that is comparable or superior to fine-tuning while dramatically reducing trainable parameters. Nevertheless, the effectiveness of such methods under the context of data augmentation, a common strategy to improve learning under low data regimes, has not been fully explored. In this paper, we examine the effectiveness of several popular task-agnostic data augmentation techniques, i.e., EDA, Back Translation, and Mixup, when using two general parameter efficient tuning methods, P-tuning v2 and LoRA, under data scarcity. We show that data augmentation can be used to boost the performance of P-tuning and LoRA models, but the effectiveness of each technique varies and certain methods can lead to a notable degradation in performance, particularly when using larger models and on harder tasks. We further analyze the sentence representations of P-tuning compared to fine-tuning to help understand the above behaviour, and reveal how P-tuning generally presents a more limited ability to separate the sentence embeddings from different classes of augmented data. In addition, it displays poorer performance on heavily altered data. However, we demonstrate that by adding a simple contrastive loss function it can help mitigate such issues for prefix tuning, resulting in sizable improvements to augmented data performance.

Distant supervision for relation extraction enables one to effectively acquire structured relations out of very large text corpora with less human efforts. Nevertheless, most of the prior-art models for such tasks assume that the given text can be noisy, but their corresponding labels are clean. Such unrealistic assumption is contradictory with the fact that the given labels are often noisy as well, thus leading to significant performance degradation of those models on real-world data. To cope with this challenge, we propose a novel label-denoising framework that combines neural network with probabilistic modelling, which naturally takes into account the noisy labels during learning. We empirically demonstrate that our approach significantly improves the current art in uncovering the ground-truth relation labels.

We propose a novel strategy to encode the syntax parse tree of sentence into a learnable distributed representation. The proposed syntax encoding scheme is provably information-lossless. In specific, an embedding vector is constructed for each word in the sentence, encoding the path in the syntax tree corresponding to the word. The one-to-one correspondence between these “syntax-embedding” vectors and the words (hence their embedding vectors) in the sentence makes it easy to integrate such a representation with all word-level NLP models. We empirically show the benefits of the syntax embeddings on the Authorship Attribution domain, where our approach improves upon the prior art and achieves new performance records on five benchmarking data sets.

While natural languages are compositional, how state-of-the-art neural models achieve compositionality is still unclear. We propose a deep network, which not only achieves competitive accuracy for text classification, but also exhibits compositional behavior. That is, while creating hierarchical representations of a piece of text, such as a sentence, the lower layers of the network distribute their layer-specific attention weights to individual words. In contrast, the higher layers compose meaningful phrases and clauses, whose lengths increase as the networks get deeper until fully composing the sentence.