Related papers: Automatic Alignment of Discourse Relations of Diff…

Due to the absence of explicit connectives, implicit discourse relation recognition (IDRR) remains a challenging task in discourse analysis. The critical step for IDRR is to learn high-quality discourse relation representations between two…

Slot filling and intent detection are two fundamental tasks in the field of natural language understanding. Due to the strong correlation between these two tasks, previous studies make efforts on modeling them with multi-task learning or…

Metric learning projects samples into an embedded space, where similarities and dissimilarities are quantified based on their learned representations. However, existing methods often rely on label-guided representation learning, where…

In the near future, more and more machines will perform tasks in the vicinity of human spaces or support them directly in their spatially bound activities. In order to simplify the verbal communication and the interaction between robotic…

Pre-trained vision-language models learn massive data to model unified representations of images and natural languages, which can be widely applied to downstream machine learning tasks. In addition to zero-shot inference, in order to better…

Contrastive learning has become a popular approach in natural language processing, particularly for the learning of sentence embeddings. However, the discrete nature of natural language makes it difficult to ensure the quality of positive…

Pre-trained large language models, such as ChatGPT, archive outstanding performance in various reasoning tasks without supervised training and were found to have outperformed crowdsourcing workers. Nonetheless, ChatGPT's performance in the…

Implicit discourse relation recognition (IDRR) aims at recognizing the discourse relation between two text segments without an explicit connective. Recently, the prompt learning has just been applied to the IDRR task with great performance…

Learning to construct text representations in end-to-end systems can be difficult, as natural languages are highly compositional and task-specific annotated datasets are often limited in size. Methods for directly supervising language…

Identifying intents from dialogue utterances forms an integral component of task-oriented dialogue systems. Intent-related tasks are typically formulated either as a classification task, where the utterances are classified into predefined…

Modeling complex subjective tasks in Natural Language Processing, such as recognizing emotion and morality, is considerably challenging due to significant variation in human annotations. This variation often reflects reasonable differences…

The lack of annotated data in many languages is a well-known challenge within the field of multilingual natural language processing (NLP). Therefore, many recent studies focus on zero-shot transfer learning and joint training across…

Multi-party dialogues are more difficult for models to understand than one-to-one two-party dialogues, since they involve multiple interlocutors, resulting in interweaving reply-to relations and information flows. To step over these…

Identifying breakdowns in ongoing dialogues helps to improve communication effectiveness. Most prior work on this topic relies on human annotated data and data augmentation to learn a classification model. While quality labeled dialogue…

The current trend in automatic speech recognition is to leverage large amounts of labeled data to train supervised neural network models. Unfortunately, obtaining data for a wide range of domains to train robust models can be costly.…

Statistical decision algorithms are increasingly deployed in domains where ground-truth labels are hard to obtain, such as hiring, university admissions, and content moderation. In these settings, models are typically trained on historical…

Prior approaches to realizing mixed-initiative human--computer referential communication have adopted information-state or collaborative problem-solving approaches. In this paper, we argue for a new approach, inspired by coherence-based…

Today, there have been many achievements in learning the association between voice and face. However, most previous work models rely on cosine similarity or L2 distance to evaluate the likeness of voices and faces following contrastive…

In this paper, we study the classification problem in which we have access to easily obtainable surrogate for true labels, namely complementary labels, which specify classes that observations do \textbf{not} belong to. Let $Y$ and $\bar{Y}$…

While paragraph embedding models are remarkably effective for downstream classification tasks, what they learn and encode into a single vector remains opaque. In this paper, we investigate a state-of-the-art paragraph embedding method…