Skip to content

Latest commit

 

History

History
21 lines (21 loc) · 1.08 KB

File metadata and controls

21 lines (21 loc) · 1.08 KB
title Transformers to Learn Hierarchical Contexts in Multiparty Dialogue for Span-based Question Answering
authors
Changmao Li
Jinho D. Choi
venue Annual Conference of the Association for Computational Linguistics (ACL)
year 2020
published 2020-07-06
publicationType conference
venueUrl https://acl2020.org/
paperUrl https://aclanthology.org/2020.acl-main.505/
abstract We introduce a novel approach to transformers that learns hierarchical representations in multiparty dialogue. First, three language modeling tasks are used to pre-train the transformers, tokenand utterance-level language modeling and utterance order prediction, that learn both token and utterance embeddings for better understanding in dialogue contexts. Then, multi-task learning between the utterance prediction and the token span prediction is applied to fine-tune for span-based question answering (QA). Our approach is evaluated on the FriendsQA dataset and shows improvements of 3.8% and 1.4% over the two state-of-the-art transformer models, BERT and RoBERTa, respectively.