Collecting and annotating task-oriented dialogues is time-consuming and costly; thus, zero and few shot learning could greatly benefit dialogue state tracking (DST). In this work, we …
J Feng, Q Sun, C Xu, P Zhao, Y Yang, C Tao… - arXiv preprint arXiv …, 2022 - arxiv.org
Responding with multi-modal content has been recognized as an essential capability for an intelligent conversational agent. In this paper, we introduce the MMDialog dataset to better …
D Li, H Zhang, Y Li, S Yang - arXiv preprint arXiv:2310.13231, 2023 - arxiv.org
In this work, we tackle the scenario of understanding characters in scripts, which aims to learn the characters' personalities and identities from their utterances. We begin by …
While textual information significantly enhances the performance of pre-trained language models (PLMs) in knowledge graph completion (KGC), the static and noisy nature of existing …
Z Zhang, H Zhao - arXiv preprint arXiv:2105.10956, 2021 - arxiv.org
Pre-trained language models (PrLMs) have demonstrated superior performance due to their strong ability to learn universal language representations from self-supervised pre-training …
W Deng, J Pei, Z Ren, Z Chen, P Ren - Transactions of the …, 2023 - direct.mit.edu
Answer selection in open-domain dialogues aims to select an accurate answer from candidates. The recent success of answer selection models hinges on training with large …
Recent data-driven conversational models are able to return fluent, consistent, and informative responses to many kinds of requests and utterances in task-oriented scenarios …
In this paper, we investigate the task of response ranking in conversational legal search. We propose a novel method for conversational passage response retrieval (ConvPR) for long …
T Hong, J Cho, H Yu, Y Ko, J Seo - Computer Speech & Language, 2023 - Elsevier
As knowledge-grounded dialogue systems are attracting intense research interest, technology that facilitates reference to various types of external knowledge as dialogue …