Lune

EMNLP Findings2021

Self- and Pseudo-self-supervised Prediction of Speaker and Key-utterance for Multi-party Dialogue Reading Comprehension

Yiyang Li, Hai Zhao

Abstract

Multi-party dialogue machine reading comprehension (MRC) brings tremendous challenge since it involves multiple speakers at one dialogue, resulting in intricate speaker information flows and noisy dialogue contexts. To alleviate such difficulties, previous models focus on how to incorporate these information using complex graph-based modules and additional manually labeled data, which is usually rare in real scenarios. In this paper, we design two labour-free self-and pseudo-selfsupervised prediction tasks on speaker and key-utterance to implicitly model the speaker information flows, and capture salient clues in a long dialogue. Experimental results on two benchmark datasets have justified the effectiveness of our method over competitive baselines and current state-of-the-art models.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

4 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Filling the Gap of Utterance-aware and Speaker-aware Representation for Multi-turn Dialogue cites ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators
  • Filling the Gap of Utterance-aware and Speaker-aware Representation for Multi-turn Dialogue cites MuTual: A Dataset for Multi-Turn Dialogue Reasoning
  • Back to the Future: Bidirectional Information Decoupling Network for Multi-turn Dialogue Modeling cites ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
  • Back to the Future: Bidirectional Information Decoupling Network for Multi-turn Dialogue Modeling cites ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators
  • Back to the Future: Bidirectional Information Decoupling Network for Multi-turn Dialogue Modeling cites MuTual: A Dataset for Multi-Turn Dialogue Reasoning
  • EM Pre-training for Multi-party Dialogue Response Generation cites ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators
  • Pre-training Multi-party Dialogue Models with Latent Discourse Inference cites Back to the Future: Bidirectional Information Decoupling Network for Multi-turn Dialogue Modeling
  • Pre-training Multi-party Dialogue Models with Latent Discourse Inference cites EM Pre-training for Multi-party Dialogue Response Generation
  • Pre-training Multi-party Dialogue Models with Latent Discourse Inference cites ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers4

  1. Back to the Future: Bidirectional Information Decoupling Network for Multi-turn Dialogue ModelingYiyang Li, Hai Zhao, Zhuosheng ZhangEMNLP 2022 · 9 citations
  2. EM Pre-training for Multi-party Dialogue Response GenerationYiyang Li, Hai ZhaoACL 2023 · 9 citations
  3. Pre-training Multi-party Dialogue Models with Latent Discourse InferenceYiyang Li, Xinting Huang, Wei Bi, Hai ZhaoACL 2023 · 3 citations
  4. Multi-level Contrastive Learning for Script-based Character UnderstandingDawei Li, Hengyuan Zhang, Yanran Li, Shiping YangEMNLP 2023 · 2 citations

Builds on7

  1. ALBERT: A Lite BERT for Self-supervised Learning of Language RepresentationsZhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel et al.ICLR 2020 · 7,418 citations
  2. ELECTRA: Pre-training Text Encoders as Discriminators Rather Than GeneratorsKevin Clark, Minh-Thang Luong, Quoc V. Le, Christopher D. ManningICLR 2020 · 541 citations
  3. MuTual: A Dataset for Multi-Turn Dialogue ReasoningLeyang Cui, Yu Wu, Shujie Liu, Yue Zhang et al.ACL 2020 · 115 citations
  4. Dialogue-Based Relation ExtractionDian Yu, Kai Sun, Claire Cardie, Dong YuACL 2020 · 106 citations
  5. Filling the Gap of Utterance-aware and Speaker-aware Representation for Multi-turn DialogueLongxiang Liu, Zhuosheng Zhang, Hai Zhao, Xi Zhou et al.AAAI 2021 · 57 citations

Related papers

  1. Question-Interlocutor Scope Realized Graph Modeling over Key Utterances for Dialogue Reading ComprehensionJiangnan Li, Mo Yu, Fandong Meng, Zheng Lin et al.ACL Findings 2023 · 3 citations
  2. MPC-BERT: A Pre-Trained Language Model for Multi-Party Conversation UnderstandingJia-Chen Gu, Chongyang Tao, Zhen-Hua Ling, Can Xu et al.ACL 2021
  3. Structural Characterization for Dialogue DisentanglementXinbei Ma, Zhuosheng Zhang, Hai ZhaoACL 2022 · 20 citations
  4. GLGR: Question-aware Global-to-Local Graph Reasoning for Multi-party Dialogue Reading ComprehensionYanling Li, Bowei Zou, Yifan Fan, Xibo Li et al.EMNLP Findings 2023 · 5 citations
  5. A Self-Training Method for Machine Reading Comprehension with Soft Evidence ExtractionYilin Niu, Fangkai Jiao, Mantong Zhou, Ting Yao et al.ACL 2020 · 33 citations
Dusk over the sea between two cliffs drawn in fine vertical lines