Discourse Coherence and Response-Guided Context Rewriting for Multi-Party Dialogue Generation
Previous research on multi-party dialogue generation has predominantly leveraged structural information inherent in dialogues to directly inform the generation process. However, the prevalence of colloquial expressions and incomplete utterances in dialogues often impedes comprehension and weakens the fidelity of dialogue structure representations, which is particularly pronounced in multi-party dialogues. In this work, we propose a novel framework DRCR (Discourse coherence and Response-guided Context Rewriting) to improve multi-party dialogue generation through dialogue context rewriting. Specifically, DRCR employs two complementary feedback signals, discourse coherence and response quality, to construct preference data for both context rewriting and response generation. Moreover, we propose a dynamic self-evolution learning method that allows the rewriter and responder to continuously enhance their capabilities through mutual interaction in an iterative training loop. Comprehensive experiments conducted on four multi-party dialogue datasets substantiate the effectiveness of DRCR.
Code (0)
등록된 구현이 없습니다.
Tasks
Dialogue GenerationResponse GenerationSimilar Papers 제목 키워드 기반
Differentially-Private Text Rewriting reshapes Linguistic Style
Differential Privacy (DP) for text matured from disjointed word-level substitutions to contiguous sentence-level rewriting by leveraging the generative capacity of language models. While this form of text privatization i…
Using Rhetorical Structure Theory to Assess Discourse Coherence for Non-native Spontaneous Speech
This study aims to model the discourse structure of spontaneous spoken responses within the context of an assessment of English speaking proficiency for non-native speakers. Rhetorical Structure Theory (RST) has been com…
DialogBERT: Discourse-Aware Response Generation via Learning to Recover and Rank Utterances
Recent advances in pre-trained language models have significantly improved neural response generation. However, existing methods usually view the dialogue context as a linear sequence of tokens and learn to generate the …
Conversational Response GenerationResponse GenerationDiscourse Graph Guided Document Translation with Large Language Models
Adapting large language models to full document translation remains challenging due to the difficulty of capturing long-range dependencies and preserving discourse coherence throughout extended texts. While recent agenti…
Machine TranslationA General Contextualized Rewriting Framework for Text Summarization
The rewriting method for text summarization combines extractive and abstractive approaches, improving the conciseness and readability of extractive summaries using an abstractive model. Exiting rewriting systems take eac…
reinforcement-learningReinforcement Learning (RL)SentenceTAG+1