Chat More If You Like: Dynamic Cue Words Planning to Flow Longer Conversations
To build an open-domain multi-turn conversation system is one of the most interesting and challenging tasks in Artificial Intelligence. Many research efforts have been dedicated to building such dialogue systems, yet few shed light on modeling the conversation flow in an ongoing dialogue. Besides, it is common for people to talk about highly relevant aspects during a conversation. And the topics are coherent and drift naturally, which demonstrates the necessity of dialogue flow modeling. To this end, we present the multi-turn cue-words driven conversation system with reinforcement learning method (RLCw), which strives to select an adaptive cue word with the greatest future credit, and therefore improve the quality of generated responses. We introduce a new reward to measure the quality of cue words in terms of effectiveness and relevance. To further optimize the model for long-term conversations, a reinforcement approach is adopted in this paper. Experiments on real-life dataset demonstrate that our model consistently outperforms a set of competitive baselines in terms of simulated turns, diversity and human evaluation.
Code (0)
등록된 구현이 없습니다.
Tasks
DiversityReinforcement LearningSimilar Papers 제목 키워드 기반
Online Learning of HTN Methods for integrated LLM-HTN Planning
We present online learning of Hierarchical Task Network (HTN) methods in the context of integrated HTN planning and LLM-based chatbots. Methods indicate when and how to decompose tasks into subtasks. Our method learner i…
Witscript: A System for Generating Improvised Jokes in a Conversation
A chatbot is perceived as more humanlike and likeable if it includes some jokes in its output. But most existing joke generators were not designed to be integrated into chatbots. This paper presents Witscript, a novel jo…
ChatbotLanguage ModelingLanguage ModellingSentenceDo large language models resemble humans in language use?
Large language models (LLMs) such as ChatGPT and Vicuna have shown remarkable capacities in comprehending and producing language. However, their internal workings remain a black box, and it is unclear whether LLMs and ch…
SentenceWord Definitions from Large Language Models
Dictionary definitions are historically the arbitrator of what words mean, but this primacy has come under threat by recent progress in NLP, including word embeddings and generative models like ChatGPT. We present an exp…
Word EmbeddingsChatDyn: Language-Driven Multi-Actor Dynamics Generation in Street Scenes
Generating realistic and interactive dynamics of traffic participants according to specific instruction is critical for street scene simulation. However, there is currently a lack of a comprehensive method that generates…