When to Talk: Chatbot Controls the Timing of Talking during Multi-turn Open-domain Dialogue Generation
원문 초록
Despite the multi-turn open-domain dialogue systems have attracted more and more attention and made great progress, the existing dialogue systems are still very boring. Nearly all the existing dialogue models only provide a response when the user's utterance is accepted. But during daily conversations, humans always decide whether to continue to utter an utterance based on the context. Intuitively, a dialogue model that can control the timing of talking autonomously based on the conversation context can chat with humans more naturally. In this paper, we explore the dialogue system that automatically controls the timing of talking during the conversation. Specifically, we adopt the decision module for the existing dialogue models. Furthermore, modeling conversation context effectively is very important for controlling the timing of talking. So we also adopt the graph neural networks to process the context with the natural graph structure. Extensive experiments on two benchmarks show that controlling the timing of talking can effectively improve the quality of dialogue generation, and the proposed methods significantly improve the accuracy of the timing of talking. In addition, we have publicly released the codes of our proposed model.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Intent-Aware Dialogue Generation and Multi-Task Contrastive Learning for Multi-Turn Intent Classification
ZipVoice-Dialog: Non-Autoregressive Spoken Dialogue Generation with Flow Matching
Generalized Adaptive Transfer Network: Enhancing Transfer Learning in Reinforcement Learning Across Domains
SDialog: A Python Toolkit for Synthetic Dialogue Generation and Analysis
Enhancing Medical Dialogue Generation through Knowledge Refinement and Dynamic Prompt Adjustment
MEDAL: A Framework for Benchmarking LLMs as Multilingual Open-Domain Chatbots and Dialogue Evaluators
토론
이 논문과 연결된 포럼 글이 아직 없습니다.