History-Aware Conversational Dense Retrieval
- URL: http://arxiv.org/abs/2401.16659v3
- Date: Tue, 28 May 2024 13:18:29 GMT
- Title: History-Aware Conversational Dense Retrieval
- Authors: Fengran Mo, Chen Qu, Kelong Mao, Tianyu Zhu, Zhan Su, Kaiyu Huang, Jian-Yun Nie,
- Abstract summary: We propose a History-Aware Conversational Dense Retrieval (HAConvDR) system, which incorporates two ideas: context-denoised query reformulation and automatic mining of supervision signals.
Experiments on two public conversational search datasets demonstrate the improved history modeling capability of HAConvDR.
- Score: 31.203399110612388
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Conversational search facilitates complex information retrieval by enabling multi-turn interactions between users and the system. Supporting such interactions requires a comprehensive understanding of the conversational inputs to formulate a good search query based on historical information. In particular, the search query should include the relevant information from the previous conversation turns. However, current approaches for conversational dense retrieval primarily rely on fine-tuning a pre-trained ad-hoc retriever using the whole conversational search session, which can be lengthy and noisy. Moreover, existing approaches are limited by the amount of manual supervision signals in the existing datasets. To address the aforementioned issues, we propose a History-Aware Conversational Dense Retrieval (HAConvDR) system, which incorporates two ideas: context-denoised query reformulation and automatic mining of supervision signals based on the actual impact of historical turns. Experiments on two public conversational search datasets demonstrate the improved history modeling capability of HAConvDR, in particular for long conversations with topic shifts.
Related papers
- ProCIS: A Benchmark for Proactive Retrieval in Conversations [21.23826888841565]
We introduce a large-scale dataset for proactive document retrieval that consists of over 2.8 million conversations.
We conduct crowdsourcing experiments to obtain high-quality and relatively complete relevance judgments.
We also collect annotations related to the parts of the conversation that are related to each document, enabling us to evaluate proactive retrieval systems.
arXiv Detail & Related papers (2024-05-10T13:11:07Z) - Social Commonsense-Guided Search Query Generation for Open-Domain
Knowledge-Powered Conversations [66.16863141262506]
We present a novel approach that focuses on generating internet search queries guided by social commonsense.
Our proposed framework addresses passive user interactions by integrating topic tracking, commonsense response generation and instruction-driven query generation.
arXiv Detail & Related papers (2023-10-22T16:14:56Z) - History-Aware Hierarchical Transformer for Multi-session Open-domain
Dialogue System [59.78425104243993]
We propose History-Aware Hierarchical Transformer (HAHT) for multi-session open-domain dialogue.
HAHT maintains a long-term memory of history conversations and utilizes history information to understand current conversation context.
Experimental results on a large-scale Multi-Session Conversation dataset suggest that the proposed HAHT model consistently outperforms baseline models.
arXiv Detail & Related papers (2023-02-02T06:54:33Z) - End-to-end Spoken Conversational Question Answering: Task, Dataset and
Model [92.18621726802726]
In spoken question answering, the systems are designed to answer questions from contiguous text spans within the related speech transcripts.
We propose a new Spoken Conversational Question Answering task (SCQA), aiming at enabling the systems to model complex dialogue flows.
Our main objective is to build the system to deal with conversational questions based on the audio recordings, and to explore the plausibility of providing more cues from different modalities with systems in information gathering.
arXiv Detail & Related papers (2022-04-29T17:56:59Z) - BERT-CoQAC: BERT-based Conversational Question Answering in Context [10.811729691130349]
We introduce a framework based on a publically available pre-trained language model called BERT for incorporating history turns into the system.
Experiment results revealed that our framework is comparable in performance with the state-of-the-art models on the QuAC leader board.
arXiv Detail & Related papers (2021-04-23T03:05:17Z) - A Graph-guided Multi-round Retrieval Method for Conversational
Open-domain Question Answering [52.041815783025186]
We propose a novel graph-guided retrieval method to model the relations among answers across conversation turns.
We also propose to incorporate the multi-round relevance feedback technique to explore the impact of the retrieval context on current question understanding.
arXiv Detail & Related papers (2021-04-17T04:39:41Z) - BERT Embeddings Can Track Context in Conversational Search [5.3222282321717955]
We develop a conversational search system that helps people search for information in a natural way.
System is able to understand the context where the question is posed, tracking the current state of the conversation and detecting mentions to previous questions and answers.
arXiv Detail & Related papers (2021-04-13T22:02:24Z) - Open-Retrieval Conversational Question Answering [62.11228261293487]
We introduce an open-retrieval conversational question answering (ORConvQA) setting, where we learn to retrieve evidence from a large collection before extracting answers.
We build an end-to-end system for ORConvQA, featuring a retriever, a reranker, and a reader that are all based on Transformers.
arXiv Detail & Related papers (2020-05-22T19:39:50Z) - Multi-Stage Conversational Passage Retrieval: An Approach to Fusing Term
Importance Estimation and Neural Query Rewriting [56.268862325167575]
We tackle conversational passage retrieval (ConvPR) with query reformulation integrated into a multi-stage ad-hoc IR system.
We propose two conversational query reformulation (CQR) methods: (1) term importance estimation and (2) neural query rewriting.
For the former, we expand conversational queries using important terms extracted from the conversational context with frequency-based signals.
For the latter, we reformulate conversational queries into natural, standalone, human-understandable queries with a pretrained sequence-tosequence model.
arXiv Detail & Related papers (2020-05-05T14:30:20Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.