Lune

EMNLP Findings2023

Explicit Alignment and Many-to-many Entailment Based Reasoning for Conversational Machine Reading

Yangyang Luo, Shiyu Tian, Caixia Yuan, Xiaojie Wang

Abstract

Conversational Machine Reading (CMR) requires answering a user's initial question through multi-turn dialogue interactions based on a given document. Although there exist many effective methods, they largely neglected the alignment between the document and the user-provided information, which significantly affects the intermediate decisionmaking and subsequent follow-up question generation. To address this issue, we propose a pipeline framework that (1) aligns the aforementioned two sides in an explicit way, (2) makes decisions using a lightweight many-tomany entailment reasoning module, and (3) directly generates follow-up questions based on the document and previously asked questions. Our proposed method achieves state-of-the-art in micro-accuracy and ranks the first place on the public leaderboard 1 of the CMR benchmark dataset ShARC.

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.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

Builds onCited byLeft to right by year; the more cited, the higher.

Builds on9

  1. Training language models to follow instructions with human feedbackLong Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida et al.NeurIPS 2022 · 24,707 citations
  2. BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and ComprehensionMike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad et al.ACL 2020 · 1,224 citations
  3. Semantics-Aware BERT for Language UnderstandingZhuosheng Zhang, Yuwei Wu, Hai Zhao, Zuchao Li et al.AAAI 2020 · 396 citations
  4. DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding SharingPengcheng He, Jianfeng Gao, Weizhu ChenICLR 2023 · 394 citations
  5. Discern: Discourse-Aware Entailment Reasoning Network for Conversational Machine ReadingYifan Gao, Chien-Sheng Wu, Jingjing Li, Shafiq R. Joty et al.EMNLP 2020 · 47 citations

Related papers

  1. Explicit Memory Tracker with Coarse-to-Fine Reasoning for Conversational Machine ReadingYifan Gao, Chien-Sheng Wu, Shafiq R. Joty, Caiming Xiong et al.ACL 2020 · 18 citations
  2. Smoothing Dialogue States for Open Conversational Machine ReadingZhuosheng Zhang, Siru Ouyang, Hai Zhao, Masao Utiyama et al.EMNLP 2021 · 4 citations
  3. Bridging The Gap: Entailment Fused-T5 for Open-retrieval Conversational Machine Reading ComprehensionXiao Zhang, Heyan Huang, Zewen Chi, Xian-Ling MaoACL 2023 · 3 citations
  4. Dialogue Graph Modeling for Conversational Machine ReadingSiru Ouyang, Zhuosheng Zhang, Hai ZhaoACL Findings 2021 · 31 citations
  5. ChatR1: Reinforcement Learning for Conversational Reasoning and Retrieval Augmented Question AnsweringSimon Lupart, Mohammad Aliannejadi, Evangelos KanoulasACL 2026 · 5 citations
Dusk over the sea between two cliffs drawn in fine vertical lines