ACL Findings2023
Focus-aware Response Generation in Inquiry Conversation
Yiquan Wu, Weiming Lu, Yating Zhang, Adam Jatowt, Jun Feng, Changlong Sun, Fei Wu, Kun Kuang
Abstract
Inquiry conversation is a common form of conversation that aims to complete the investigation (e.g., court hearing, medical consultation and police interrogation) during which a series of focus shifts occurs. While many models have been proposed to generate a smooth response to a given conversation history, neglecting the focus can limit performance in inquiry conversation where the order of the focuses plays there a key role. In this paper, we investigate the problem of response generation in inquiry conversation by taking the focus into consideration. We propose a novel Focusaware Response Generation (FRG) method by jointly optimizing a multi-level encoder and a set of focal decoders to generate several candidate responses that correspond to different focuses. Additionally, a focus ranking module is proposed to predict the next focus and rank the candidate responses. Experiments on two orthogonal inquiry conversation datasets (judicial, medical domain) demonstrate that our method generates results significantly better in automatic metrics and human evaluation compared to the state-of-the-art approaches.
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.
6 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- ART: rule bAsed futuRe-inference deducTion cites De-Biased Court's View Generation with Causality
- ART: rule bAsed futuRe-inference deducTion cites Towards Interactivity and Interpretability: A Rationale-based Legal Judgment Prediction Framework
- De-biased Attention Supervision for Text Classification with Causality cites De-Biased Court's View Generation with Causality
- De-biased Attention Supervision for Text Classification with Causality cites Intelligent Model Update Strategy for Sequential Recommendation
- De-biased Attention Supervision for Text Classification with Causality cites Towards Interactivity and Interpretability: A Rationale-based Legal Judgment Prediction Framework
- De-Biased Court's View Generation with Causality cites BERTScore: Evaluating Text Generation with BERT
- Towards Interactivity and Interpretability: A Rationale-based Legal Judgment Prediction Framework cites De-Biased Court's View Generation with Causality
- An Expression Tree Decoding Strategy for Mathematical Equation Generation cites De-Biased Court's View Generation with Causality
- An Expression Tree Decoding Strategy for Mathematical Equation Generation cites Towards Interactivity and Interpretability: A Rationale-based Legal Judgment Prediction Framework
- MProto: Multi-Prototype Network with Denoised Optimal Transport for Distantly Supervised Named Entity Recognition cites De-Biased Court's View Generation with Causality
Cited by top-tier papers6
- Intelligent Model Update Strategy for Sequential RecommendationZheqi Lv, Wenqiao Zhang, Zhengyu Chen, Shengyu Zhang et al.WWW 2024 · 53 citations
- De-biased Attention Supervision for Text Classification with CausalityYiquan Wu, Yifei Liu, Ziyu Zhao, Weiming Lu et al.AAAI 2024 · 10 citations
- MProto: Multi-Prototype Network with Denoised Optimal Transport for Distantly Supervised Named Entity RecognitionShuhui Wu, Yongliang Shen, Zeqi Tan, Wenqi Ren et al.EMNLP 2023 · 4 citations
- An Expression Tree Decoding Strategy for Mathematical Equation GenerationWenqi Zhang, Yongliang Shen, Qingpeng Nong, Zeqi Tan et al.EMNLP 2023 · 3 citations
- ART: rule bAsed futuRe-inference deducTionMengze Li, Tianqi Zhao, Jionghao Bai, Baoyi He et al.EMNLP 2023 · 2 citations
Builds on9
- BERTScore: Evaluating Text Generation with BERTTianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q. Weinberger et al.ICLR 2020 · 8,443 citations
- Cross-Modality Mutual Learning for Enhancing Smart Contract Vulnerability Detection on BytecodePeng Qian, Zhenguang Liu, Yifang Yin, Qinming HeWWW 2023 · 91 citations
- A Controllable Model of Grounded Response GenerationZeqiu Wu, Michel Galley, Chris Brockett, Yizhe Zhang et al.AAAI 2021 · 89 citations
- De-Biased Court's View Generation with CausalityYiquan Wu, Kun Kuang, Yating Zhang, Xiaozhong Liu et al.EMNLP 2020 · 71 citations
- Towards Interactivity and Interpretability: A Rationale-based Legal Judgment Prediction FrameworkYiquan Wu, Yifei Liu, Weiming Lu, Yating Zhang et al.EMNLP 2022 · 33 citations
Related papers
- Response-conditioned Turn-taking PredictionBing'er Jiang, Erik Ekstedt, Gabriel SkantzeACL Findings 2023 · 3 citations
- CARE: Causality Reasoning for Empathetic Responses by Conditional Graph GenerationJiashuo Wang, Yi Cheng, Wenjie LiEMNLP Findings 2022 · 11 citations
- Improving Empathetic Response Generation by Recognizing Emotion Cause in ConversationsJun Gao, Yuhan Liu, Haolin Deng, Wei Wang et al.EMNLP Findings 2021 · 87 citations
- Modeling Transitions of Focal Entities for Conversational Knowledge Base Question AnsweringYunshi Lan, Jing JiangACL 2021
- The World is Not Binary: Learning to Rank with Grayscale Data for Dialogue Response SelectionZibo Lin, Deng Cai, Yan Wang, Xiaojiang Liu et al.EMNLP 2020 · 32 citations
