activity
20192021
most citedDomain-Adaptive Pretraining Methods for Dialogue Understanding

2 citations · 6 across the 7 of their papers we have counts for

collaborators

9 papers

cs.CL2021

Exophoric Pronoun Resolution in Dialogues with Topic Regularization

Xintong Yu, Hongming Zhang, Yangqiu Song +3

Resolving pronouns to their referents has long been studied as a fundamental natural language understanding problem. Previous works on pronoun coreference resolution (PCR) mostly f…

cs.CL2021

CSAGN: Conversational Structure Aware Graph Network for Conversational Semantic Role Labeling

Han Wu, Kun Xu, Linqi Song

Conversational semantic role labeling (CSRL) is believed to be a crucial step towards dialogue understanding. However, it remains a major challenge for existing CSRL parser to hand…

cs.CL20212 cited

Domain-Adaptive Pretraining Methods for Dialogue Understanding

Han Wu, Kun Xu, Linfeng Song +3

Language models like BERT and SpanBERT pretrained on open-domain data have obtained impressive gains on various NLP tasks. In this paper, we probe the effectiveness of domain-adapt…

cs.CL20211 cited

Joint Coreference Resolution and Character Linking for Multiparty Conversation

Jiaxin Bai, Hongming Zhang, Yangqiu Song +1

Character linking, the task of linking mentioned people in conversations to the real world, is crucial for understanding the conversations. For the efficiency of communication, hum…

cs.CL20201 cited

Coordinated Reasoning for Cross-Lingual Knowledge Graph Alignment

Kun Xu, Linfeng Song, Yansong Feng +2

Existing entity alignment methods mainly vary on the choices of encoding the knowledge graph, but they typically use the same decoding method, which independently chooses the local…

cs.CL20201 cited

Multiplex Word Embeddings for Selectional Preference Acquisition

Hongming Zhang, Jiaxin Bai, Yan Song +5

Conventional word embeddings represent words with fixed vectors, which are usually trained based on co-occurrence patterns among words. In doing so, however, the power of such repr…