Query Enhanced Knowledge-Intensive Conversation via Unsupervised Joint Modeling
In this paper, we propose an unsupervised query enhanced approach for knowledge-intensive conversations, namely QKConv. There are three modules in QKConv: a query generator, an off-the-shelf knowledge selector, and a response generator. QKConv is optimized through joint training, which produces the response by exploring multiple candidate queries and leveraging corresponding selected knowledge. The joint training solely relies on the dialogue context and target response, getting exempt from extra query annotations or knowledge provenances. To evaluate the effectiveness of the proposed QKConv, we conduct experiments on three representative knowledge-intensive conversation datasets: conversational question-answering, task-oriented dialogue, and knowledge-grounded conversation. Experimental results reveal that QKConv performs better than all unsupervised methods across three datasets and achieves competitive performance compared to supervised methods.
Code (3)
Tasks
Conversational Question AnsweringQuestion AnsweringRetrievalSimilar Papers 제목 키워드 기반
Conversational Query Rewriting with Self-supervised Learning
Context modeling plays a critical role in building multi-turn dialogue systems. Conversational Query Rewriting (CQR) aims to simplify the multi-turn dialogue modeling into a single-turn problem by explicitly rewriting th…
Self-Supervised LearningKIMAs: A Configurable Knowledge Integrated Multi-Agent System
Knowledge-intensive conversations supported by large language models (LLMs) have become one of the most popular and helpful applications that can assist people in different aspects. Many current knowledge-intensive appli…
ManagementRAGRetrievalRetrieval-augmented GenerationHint-enhanced In-Context Learning wakes Large Language Models up for knowledge-intensive tasks
In-context learning (ICL) ability has emerged with the increasing scale of large language models (LLMs), enabling them to learn input-label mappings from demonstrations and perform well on downstream tasks. However, unde…
In-Context LearningOpen-Domain Question AnsweringQuestion AnsweringTackling Query-Focused Summarization as A Knowledge-Intensive Task: A Pilot Study
Query-focused summarization (QFS) requires generating a summary given a query using a set of relevant documents. However, such relevant documents should be annotated manually and thus are not readily available in realist…
Open-Domain Question AnsweringPassage RetrievalQuery-focused SummarizationQuestion Answering+2TREC CAsT 2019: The Conversational Assistance Track Overview
The Conversational Assistance Track (CAsT) is a new track for TREC 2019 to facilitate Conversational Information Seeking (CIS) research and to create a large-scale reusable test collection for conversational search syste…
Conversational SearchLearning-To-RankMachine Reading ComprehensionReading Comprehension+2