arXiv 0908.07092009-08-05cs.IRcs.HC

Toward Collaborative Information Seeking (CIS)

Chirag Shah

备注：: Presented at 1st Intl Workshop on Collaborative Information Seeking, 2008 (arXiv:0908.0583)

英文摘要：

It is natural for humans to collaborate while dealing with complex problems. In this article I consider this process of collaboration in the context of information seeking. The study and discussion presented here are driven by two dissatisfactions: (1) the majority of IR systems today do not facilitate collaboration directly, and (2) the concept of collaboration itself is not well-understood. I begin by probing the notion of collaboration and propose a model that helps us understand the requirements for a successful collaboration. A model of a Collaborative Information Seeking (CIS) environment is then rendered based on an extended model of information seeking.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

Conversational Information Seeking

University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）；RMIT University（皇家墨尔本理工大学）；University of Glasgow（格拉斯哥大学）；Google Research（谷歌研究院）

Conversational information seeking (CIS) is concerned with a sequence of interactions between one or more users and an information system. Interactions in CIS are primarily based on natural language dialogue, while they may include other types of interactions, such as click, touch, and body gestures. This monograph provides a thorough overview of CIS definitions, applications, interactions, interfaces, design, implementation, and evaluation. This monograph views CIS applications as including conversational search, conversational question answering, and conversational recommendation. Our aim is…

2023-01-25cs.CLcs.HCcs.IR

Macaw: An Extensible Conversational Information Seeking Platform

Microsoft AI & Research（微软人工智能与研究部）

Conversational information seeking (CIS) has been recognized as a major emerging research area in information retrieval. Such research will require data and tools, to allow the implementation and study of conversational systems. This paper introduces Macaw, an open-source framework with a modular architecture for CIS research. Macaw supports multi-turn, multi-modal, and mixed-initiative interactions, and enables research for tasks such as document retrieval, question answering, recommendation, and structured data exploration. It has a modular design to encourage the study of new CIS algorithms…

2019-12-18cs.CLcs.HCcs.IR

Evaluating Collaborative Search Interfaces with Information Seeking Theory

Despite the many implicit references to the social aspects of search within Information Seeking and Retrieval research, there has been relatively little work that has specifically investigated the additional requirements for collaborative search software. In this paper we re-assess a recent evaluation framework, designed for individual information seeking experiences, to see a) how it could still be applied to collaborative search software; b) how it could produce additional requirements for collaborative search; and c) how it could be extended in future work to be even more appropriate for co…

2009-08-05cs.HCcs.IR

面向对话式信息检索系统的基于事实依据且透明的响应生成

Grounded and Transparent Response Generation for Conversational Information-Seeking Systems

本研究提出面向对话式信息检索系统的响应生成方法，通过获取置信度增强的信息片段、自动检测错误响应并透明传达系统局限性，生成基于检索段落且增强可信度的响应。

2024-06-27cs.IR

Proceedings of 1st International Workshop on Collaborative Information Seeking

The goal of the workshop is to bring together researchers interested in various aspects of small-team collaborative search to share ideas, to stimulate research in the area, and to increase the visibility of this emerging area. We expect to identify promising directions for further exploration and to establish collaborative links among research groups. The workshop took place on June 20, 2008 in Pittsburgh, Pennsylvania, USA, in conjunction with the JCDL 2008 conference. The workshop was organized around three themes: practices, models, and evaluation. We started with a discussion (still ongoi…

2009-08-07cs.HCcs.IR

Voice Information Retrieval In Collaborative Information Seeking

Voice information retrieval is a technique that provides Information Retrieval System with the capacity to transcribe spoken queries and use the text output for information search. CIS is a field of research that involves studying the situation, motivations, and methods for people working in a collaborative group for information seeking projects, as well as building a system for supporting such activities. Humans find it easier to communicate and express ideas via speech. Existing voice search like Google and other mainstream voice search does not support collaborative search. The spoken speec…

2021-10-05cs.IR

更多相关论文收起更多论文

ISEEQ: Information Seeking Question Generation using Dynamic Meta-Information Retrieval and Knowledge Graphs

AI Institute, University of South Carolina（南卡罗来纳大学人工智能研究所）；Samsung Research America（三星美国研究院）

Conversational Information Seeking (CIS) is a relatively new research area within conversational AI that attempts to seek information from end-users in order to understand and satisfy users' needs. If realized, such a system has far-reaching benefits in the real world; for example, a CIS system can assist clinicians in pre-screening or triaging patients in healthcare. A key open sub-problem in CIS that remains unaddressed in the literature is generating Information Seeking Questions (ISQs) based on a short initial query from the end-user. To address this open problem, we propose Information SE…

2021-12-13cs.AIcs.CLcs.IR

InterDeepResearch：通过交互式深度研究实现人机协作的信息检索

InterDeepResearch: Enabling Human-Agent Collaborative Information Seeking through Interactive Deep Research

本文提出InterDeepResearch系统，通过交互式深度研究框架提升人机协作信息检索效率，实验证明其在性能和用户研究支持方面具有竞争力。

2026-03-13cs.HCcs.IR

HAGRID：一个用于带归属的生成式信息检索的人机协作数据集

HAGRID: A Human-LLM Collaborative Dataset for Generative Information-Seeking with Attribution

University of Waterloo（滑铁卢大学）

本文提出 HAGRID 数据集，通过人类与 LLM 协作构建端到端生成式信息检索模型，基于 MIRACL 英文子集，利用 GPT-3.5 生成带归属解释并由人工评估，促进信息检索模型的归属能力发展。

2023-07-31cs.CLcs.IR

Wizard of Search Engine: Access to Information Through Conversations with Search Engines

Shandong University（山东大学）；University of Amsterdam（阿姆斯特丹大学）；Ahold Delhaize（阿霍德德尔海兹集团）

Conversational information seeking (CIS) is playing an increasingly important role in connecting people to information. Due to the lack of suitable resource, previous studies on CIS are limited to the study of theoretical/conceptual frameworks, laboratory-based user studies, or a particular aspect of CIS (e.g., asking clarifying questions). In this work, we make efforts to facilitate research on CIS from three aspects. (1) We formulate a pipeline for CIS with six sub-tasks: intent detection (ID), keyphrase extraction (KE), action prediction (AP), query selection (QS), passage selection (PS), a…

2021-05-18cs.CLcs.IR

通过RAG助手获取信息：在人机协作中模型大小是否重要？

Seeking Information with RAG-Assistants: Does Model Size Matter in Human-AI Collaborations?

Leiden University（莱顿大学）；TNO（荷兰代尔夫特理工大学）；TU Delft（代尔夫特理工大学）

研究评估基于RAG的助手在真实多轮信息检索场景中的表现，探讨模型大小对人机协作动态及用户感知的影响，发现混合系统在信息检索中具有优势。

2026-05-01cs.AIcs.HCcs.IR

TREC CAsT 2019: The Conversational Assistance Track Overview

University of Glasgow（格拉斯哥大学）；Microsoft Research（微软研究院）；Carnegie Mellon University（卡内基梅隆大学）

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 systems. The document corpus is 38,426,252 passages from the TREC Complex Answer Retrieval (CAR) and Microsoft MAchine Reading COmprehension (MARCO) datasets. Eighty information seeking dialogues (30 train, 50 test) are an average of 9 to 10 questions long. Relevance assessments are provided for 30 training topics and 20 test topics. This year 21 groups submitted a total of 65 runs …

2020-03-30cs.CLcs.IRcs.LG

进入未知的未知：通过参与语言模型智能体对话实现参与式人类学习

Into the Unknown Unknowns: Engaged Human Learning through Participation in Language Model Agent Conversations

Yale University（耶鲁大学）；Stanford University（斯坦福大学）

针对用户在未知未知领域中难以探索信息的问题，本文提出 Co-STORM 框架，让用户观察并引导多个语言模型智能体对话以偶然发现新知识，并通过动态思维导图和综合报告辅助学习，在自动评估和人类评估中均优于搜索引擎与 RAG 聊天机器人。

2024-10-17cs.AIcs.CLcs.IR