FCM: A Fine-grained Comparison Model for Multi-turn Dialogue Reasoning
Open accessAbstract
Despite the success of neural dialogue systems in achieving high performance on the leaderboard, they cannot meet users' requirements in practice, due to their poor reasoning skills.The underlying reason is that most neural dialogue models only capture the syntactic and semantic information, but fail to model the logical consistency between the dialogue history and the generated response.Recently, a new multi-turn dialogue reasoning task has been proposed, to facilitate dialogue reasoning research.However, this task is challenging, because there are only slight differences between the illogical response and the dialogue history.How to effectively solve this challenge is still worth exploring.This paper proposes a Finegrained Comparison Model (FCM) to tackle this problem.Inspired by human's behavior in reading comprehension, a comparison mechanism is proposed to focus on the fine-grained differences in the representation of each response candidate.Specifically, each candidate representation is compared with the whole history to obtain a history consistency representation.Furthermore, the consistency signals between each candidate and the speaker's own history are considered to drive a model to prefer a candidate that is logically consistent with the speaker's history logic.Finally, the above consistency representations are employed to output a ranking list of the candidate responses for multi-turn dialogue reasoning.Experimental results on two public dialogue datasets show that our method obtains higher ranking scores than the baseline models.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
There are some reasoning works in the area of dialogue, but few in reducing hallucinations.
“There are some reasoning works in the area of dialogue [39, 83, 272], but few in reducing hallucinations.”
From Survey of Hallucination in Natural Language Generation (2023) · cites this paper as [272]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
The citation lists haven’t been fetched yet
References 35 · Cited by 4
Research works printed but not linked: 22
- Hyundong Cho and Jonathan May. 2020. Grounding conversations with improvised dialogues. In ACL.
- Kevin Clark, Urvashi Khandelwal, Omer Levy, and Christopher D. Manning. 2019. What does BERT look at? an analysis of bert's attention. CoRR.
- Jia-Chen Gu, Tianda Li, Quan Liu, Zhen-Hua Ling, Zhiming Su, Si Wei, and Xiaodan Zhu. 2020. Speaker-aware BERT for multi-turn response selec- tion in retrieval-based chatbots. CIKM.
- Jiwei Li, Will Monroe, Tianlin Shi, Sébastien Jean, Alan Ritter, and Dan Jurafsky. 2017a. Adversarial learning for neural dialogue generation. EMNLP.
- Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Man- dar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized BERT pretraining ap- proach. CoRR.
- Ryan Lowe, Nissan Pow, Iulian Serban, and Joelle Pineau. 2015. The ubuntu dialogue corpus: A large dataset for research in unstructured multi-turn dia- logue systems. SIGDIAL Conference.
- Lili Mou, Yiping Song, Rui Yan, Ge Li, Lu Zhang, and Zhi Jin. 2016. Sequence to backward and forward sequences: A content-introducing approach to gen- erative short-text conversation. COLING.
- Jiaul H. Paik. 2013. A novel TF-IDF weighting scheme for effective ranking. SIGIR.
- Sashank Santhanam and Samira Shaikh. 2019. A sur- vey of natural language generation techniques with a focus on dialogue systems -past, present and future directions. CoRR.
- Iulian V Serban, Alessandro Sordoni, Yoshua Bengio, Aaron Courville, and Joelle Pineau. 2016. Building end-to-end dialogue systems using generative hierar- chical neural network models. In AAAI.
- Chongyang Tao, Wei Wu, Can Xu, Wenpeng Hu, Dongyan Zhao, and Rui Yan. 2019b. One time of interaction may not be enough: Go deep with an interaction-over-interaction network for response se- lection in dialogues. In ACL.
- Sixing Wu, Ying Li, Dawei Zhang, Yang Zhou, and Zhonghai Wu. 2020. Diverse and informative di- alogue generation with context-specific common- sense knowledge awareness. ACL.
- Yu Wu, Wei Wu, Chen Xing, Ming Zhou, and Zhou- jun Li. 2017. Sequential matching network: A new architecture for multi-turn response selection in retrieval-based chatbots. ACL.
- Tom Young, Erik Cambria, Iti Chaturvedi, Hao Zhou, Subham Biswas, and Minlie Huang. 2018. Aug- menting end-to-end dialogue systems with common- sense knowledge. AAAI.
- Chunyuan Yuan, Wei Zhou, Mingming Li, Shangwen Lv, Fuqing Zhu, Jizhong Han, and Songlin Hu. 2019. Multi-hop selector network for multi-turn response selection in retrieval-based chatbots. EMNLP.
- Haolan Zhan, Hainan Zhang, Hongshen Chen, Zhuoye Ding, Yongjun Bao, and Yanyan Lan. 2021. Aug- menting knowledge-grounded conversations with se- quential knowledge transition. NAACL.
- Hainan Zhang, Yanyan Lan, Jiafeng Guo, Jun Xu, and Xueqi Cheng. 2018a. Reinforcing coherence for se- quence to sequence model in dialogue generation. IJCAI.
- Hainan Zhang, Yanyan Lan, Liang Pang, Jiafeng Guo, and Xueqi Cheng. 2019. Recosa: Detecting the rel- evant contexts with self-attention for multi-turn dia- logue generation. ACL.
- Weinan Zhang, Yiming Cui, Yifa Wang, Qingfu Zhu, Lingzhi Li, Lianqiang Zhou, and Ting Liu. 2018b. Context-sensitive generation of open-domain con- versational responses. COLING.
- Zhuosheng Zhang, Jiangtong Li, Pengfei Zhu, Hai Zhao, and Gongshen Liu. 2018c. Modeling multi- turn conversation with deep utterance aggregation. COLING.
- Xiangyang Zhou, Lu Li, Daxiang Dong, Yi Liu, Ying Chen, Wayne Xin Zhao, Dianhai Yu, and Hua Wu. 2018. Multi-turn response selection for chatbots with deep attention matching network. ACL.
- Haichao Zhu, Furu Wei, Bing Qin, and Ting Liu. 2018. Hierarchical attention flow for multiple-choice read- ing comprehension. In AAAI.
- Authors
- Wang, X., Zhang, H., Zhao, S., Zou, Y., Chen, H., Ding, Z., Cheng, B., & Lan, Y.
- Affiliations
- Beijing University of Posts and Telecommunications (CN)
- Jingdong (China) (CN)
- Tsinghua University (CN)
- Venue
- Findings of the Association for Computational Linguistics: EMNLP 2021
- Published
- 2021
- Pages
- 4284-4293
- OpenAlex
- W3198967775
- Cited by
- 4
- References
- 35
- Citations by year
- 2023: 3 · 2022: 1
- FWCI
- 0.46
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Natural Science Foundation of China (61773362)
- Beijing University of Posts and Telecommunications
- Beijing Nova Program (Z191100001119031)
- National Key Research and Development Program of China (2018YFB1003804)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Keywords
- logical consistency, dialogue history, response generation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
