Due to the significance and value in human-computer interaction and natural language
processing, task-oriented dialog systems are attracting more and more attention in both …

Abstractive dialogue summarization generates a concise and fluent summary covering the
salient information in a dialogue among two or more interlocutors. It has attracted significant …

In the retrieval-based multi-turn dialogue modeling, it remains a challenge to select the most
appropriate response according to extracting salient features in context utterances. As a …

Discourse structures are beneficial for various NLP tasks such as dialogue understanding,
question answering, sentiment analysis, and so on. This paper presents a deep sequential …

Dialogue topic segmentation is critical in several dialogue modeling problems. However,
popular unsupervised approaches only exploit surface features in assessing topical …

Conversation—a verbal interaction between two or more people—is a complex, pervasive,
and consequential human behavior. Conversations have been studied across many …

We consider the task of driver gaze prediction: estimating where the location of the focus of a
driver should be, based on a raw video of the outside environment. In practice, we output a …

To model the context history in multi-turn conversations has become a critical step towards a
better understanding of the user query in question answering systems. To utilize the context …

Topic segmentation is critical in key NLP tasks and recent works favor highly effective neural
supervised approaches. However, current neural solutions are arguably limited in how they …

Multi-party dialogue machine reading comprehension (MRC) raises an even more
challenging understanding goal on dialogue with more than two involved speakers …