paper-with-me

홈 › Papers

Hexa: Self-Improving for Knowledge-Grounded Dialogue System

2023-10-10 · DaeJin Jo, Daniel Wontae Nam, Gunsoo Han, Kyoung-Woon On, Taehwan Kwon, Seungeun Rho, Sungwoong Kim

A common practice in knowledge-grounded dialogue generation is to explicitly utilize intermediate steps (e.g., web-search, memory retrieval) with modular approaches. However, data for such steps are often inaccessible compared to those of dialogue responses as they are unobservable in an ordinary dialogue. To fill in the absence of these data, we develop a self-improving method to improve the generative performances of intermediate steps without the ground truth data. In particular, we propose a novel bootstrapping scheme with a guided prompt and a modified loss function to enhance the diversity of appropriate self-generated responses. Through experiments on various benchmark datasets, we empirically demonstrate that our method successfully leverages a self-improving mechanism in generating intermediate and final responses and improves the performances on the task of knowledge-grounded dialogue generation.

📄 PDF Abstract BibTeX arXiv:2310.06404

Code (0)

등록된 구현이 없습니다.

Tasks

Dialogue GenerationDiversityRetrieval

Similar Papers 제목 키워드 기반

Knowledge-Grounded Dialogue Generation with a Unified Knowledge Representation

2021-12-15 · NAACL 2022 7 · Yu Li, Baolin Peng, Yelong Shen, Yi Mao 외

Knowledge-grounded dialogue systems are challenging to build due to the lack of training data and heterogeneous knowledge sources. Existing systems perform poorly on unseen topics due to limited topics covered in the tra…

Dialogue GenerationLanguage ModelingLanguage Modelling

Knowledge-Grounded Dialogue Generation with a Unified Knowledge Representation

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Knowledge-grounded dialogue systems are challenging to build due to the lack of training data and heterogeneous knowledge sources. Existing systems perform poorly on unseen topics due to limited topics covered in the tra…

Dialogue GenerationLanguage ModelingLanguage Modelling

Using a KG-Copy Network for Non-Goal Oriented Dialogues

2019-10-17 · Debanjan Chaudhuri, Md Rashad Al Hasan Rony, Simon Jordan, Jens Lehmann

Non-goal oriented, generative dialogue systems lack the ability to generate answers with grounded facts. A knowledge graph can be considered an abstraction of the real world consisting of well-grounded facts. This paper …

Knowledge GraphsResponse Generation

Zero-Resource Knowledge-Grounded Dialogue Generation

2020-08-29 · NeurIPS 2020 12 · Linxiao Li, Can Xu, Wei Wu, Yufan Zhao 외

While neural conversation models have shown great potentials towards generating informative and engaging responses via introducing external knowledge, learning such a model often requires knowledge-grounded dialogues tha…

Dialogue Generation

STAMPsy: Towards SpatioTemporal-Aware Mixed-Type Dialogues for Psychological Counseling

2024-12-21 · Jieyi Wang, Yue Huang, Zeming Liu, Dexuan Xu 외

Online psychological counseling dialogue systems are trending, offering a convenient and accessible alternative to traditional in-person therapy. However, existing psychological counseling dialogue systems mainly focus o…

Conversational RecommendationDialogue GenerationQuestion Answering