Lune

EMNLP Findings2020

Filtering before Iteratively Referring for Knowledge-Grounded Response Selection in Retrieval-Based Chatbots

Jia-Chen Gu, Zhen-Hua Ling, Quan Liu, Zhigang Chen, Xiaodan Zhu

Abstract

The challenges of building knowledgegrounded retrieval-based chatbots lie in how to ground a conversation on its background knowledge and how to match response candidates with both context and knowledge simultaneously. This paper proposes a method named Filtering before Iteratively REferring (FIRE) for this task. In this method, a context filter and a knowledge filter are first built, which derive knowledge-aware context representations and context-aware knowledge representations respectively by global and bidirectional attention. Besides, the entries irrelevant to the conversation are discarded by the knowledge filter. After that, iteratively referring is performed between context and response representations as well as between knowledge and response representations, in order to collect deep matching features for scoring response candidates. Experimental results show that FIRE outperforms previous methods by margins larger than 2.8% and 4.1% on the PERSONA-CHAT dataset with original and revised personas respectively, and margins larger than 3.1% on the CMU DoG dataset in terms of top-1 accuracy. We also show that FIRE is more interpretable by visualizing the knowledge grounding process.

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

  • Detecting Speaker Personas from Conversational Texts cites Partner Matters! An Empirical Study on Fusing Personas for Personalized Response Selection in Retrieval-Based Chatbots
  • P5: Plug-and-Play Persona Prompting for Personalized Response Selection cites Partner Matters! An Empirical Study on Fusing Personas for Personalized Response Selection in Retrieval-Based Chatbots
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers4

  1. Partner Matters! An Empirical Study on Fusing Personas for Personalized Response Selection in Retrieval-Based ChatbotsJia-Chen Gu, Hui Liu, Zhen-Hua Ling, Quan Liu et al.SIGIR 2021 · 19 citations
  2. P5: Plug-and-Play Persona Prompting for Personalized Response SelectionJoosung Lee, Minsik Oh, Donghun LeeEMNLP 2023 · 4 citations
  3. A Pre-training Strategy for Zero-Resource Response Selection in Knowledge-Grounded ConversationsChongyang Tao, Changyu Chen, Jiazhan Feng, Ji-Rong Wen et al.ACL 2021
  4. Detecting Speaker Personas from Conversational TextsJia-Chen Gu, Zhen-Hua Ling, Yu Wu, Quan Liu et al.EMNLP 2021

Related papers

  1. You Truly Understand What I Need : Intellectual and Friendly Dialog Agents grounding Persona and KnowledgeJungwoo Lim, Myunghoon Kang, Yuna Hur, Seung Won Jeong et al.EMNLP Findings 2022 · 9 citations
  2. There Are a Thousand Hamlets in a Thousand People's Eyes: Enhancing Knowledge-grounded Dialogue with Personal MemoryTingchen Fu, Xueliang Zhao, Chongyang Tao, Ji-Rong Wen et al.ACL 2022
  3. A Graph Reasoning Network for Multi-turn Response Selection via Customized Pre-trainingYongkang Liu, Shi Feng, Daling Wang, Kaisong Song et al.AAAI 2021 · 23 citations
  4. A Disentangled-Attention Based Framework with Persona-Aware Prompt Learning for Dialogue GenerationPingsheng Liu, Zhengjie Huang, Xiechi Zhang, Linlin Wang et al.AAAI 2023 · 8 citations
  5. Well Begun is Half Done: Generator-agnostic Knowledge Pre-Selection for Knowledge-Grounded DialogueLang Qin, Yao Zhang, Hongru Liang, Jun Wang et al.EMNLP 2023 · 1 citation
Dusk over the sea between two cliffs drawn in fine vertical lines