权益分类	功能权益	普通用户	{{item.name}}会员
{{category.name}}	{{benefitItem.name}}

III: Small: Searching for Answers through Iterative Feedback

III：小：通过迭代反馈寻找答案

基本信息

批准号：
1715095
负责人：
W. Bruce Croft
金额：
$ 49.2万
依托单位：
University of Massachusetts Amherst
依托单位国家：
美国
项目类别：
Continuing Grant
财政年份：
2017
资助国家：
美国
起止时间：
2017-08-15 至 2021-07-31
项目状态：
已结题

来源：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=1715095&HistoricalAwards=false
关键词：
III Small Searching Answers through

项目摘要

In current web search engines, the response to a query is typically a series of pages that contain ranked results (search engine result pages or SERPs). The increasing use of mobile search places a premium on the use of the limited display space that is available. Similarly, voice-based search, where both questions and answers are done by voice recognition and speech generation, is becoming more common and also creates a limitation on the interaction bandwidth between the system and the user. In these situations, the ability to deliver more precise answers to a broad range of questions, rather than a ranked display of results, becomes critical. If a search system can return a ranked list of possible answers instead of documents, and a search environment may limit the user-system bandwidth, this leads to the following important research question that is the focus of this proposal -- what is the most effective way to present and interact with a ranked list of answers, where the goal is to identify one or more satisfactory answers as quickly as possible. Understanding this problem and discovering solutions to it will have a large impact on the future development of search engines.This project will work on four research tasks: (a) develop and evaluate iterative relevance feedback models for answers; (b) develop and evaluate interactive summarization techniques for answers; (c) develop and evaluate finer-grained feedback approaches for answers; (d) develop and evaluate a conversation-based model for answer retrieval. This project will be the first to study methods and models for interacting with ranked lists of answers. Many researchers are developing neural models for the factoid question-answering task, but this effort is one of just a few looking at the problem of finding non-factoid answers in passages of documents. The experience gained from developing neural models for this complex task provides the background for the unique tasks and approaches described in this proposal, which address the key, but previously ignored, issue of how we make effective use of ranked lists of answers to interact with users and improve the results from neural answer retrieval models. The later part of the project will address the use of conversational models in search, which is also becoming increasingly important but has not yet been studied.

在当前的网络搜索引擎中，对查询的响应通常是包含排名结果的一系列页面（搜索引擎结果页面或SERP）。越来越多地使用移动的搜索使得有限的可用显示空间的使用变得更加重要。类似地，基于语音的搜索，其中问题和答案都通过语音识别和语音生成来完成，变得越来越普遍，并且也对系统和用户之间的交互带宽造成了限制。在这些情况下，能够对广泛的问题提供更精确的答案，而不是排名显示结果，变得至关重要。如果一个搜索系统可以返回一个可能答案的排序列表而不是文档，并且搜索环境可能限制用户-系统带宽，这将导致以下重要的研究问题，这是本提案的重点-什么是最有效的方式来呈现和交互排序的答案列表，目标是尽快确定一个或多个满意的答案。本项目将围绕以下四个方面展开研究：（a）开发和评估用于回答的迭代相关反馈模型;（B）开发和评估用于回答的交互式摘要技术;（c）开发和评估用于回答的更细粒度反馈方法;（d）开发和评估用于回答的交互式摘要技术。（d）开发和评估一个基于对话的答案检索模型。该项目将是第一个研究与排名答案列表交互的方法和模型的项目。许多研究人员正在开发用于事实问答任务的神经模型，但这项工作只是少数几个研究在文档段落中找到非事实答案的问题之一。从为这个复杂的任务开发神经模型中获得的经验为本提案中描述的独特任务和方法提供了背景，这些任务和方法解决了关键但以前被忽视的问题，即我们如何有效地利用排名的答案列表与用户进行交互并改进神经答案检索模型的结果。该项目的后半部分将解决在搜索中使用会话模型的问题，这也变得越来越重要，但尚未得到研究。

项目成果

期刊论文数量（22）

专著数量（0）

科研奖励数量（0）

会议论文数量（0）

专利数量（0）

Asking Clarifying Questions Based on Negative Feedback in Conversational Search

DOI：
10.1145/3471158.3472232
发表时间：
2021-07
期刊：
Proceedings of the 2021 ACM SIGIR International Conference on Theory of Information Retrieval
影响因子：
0
作者：
Keping Bi;Qingyao Ai;W. Bruce Croft
通讯作者：
Keping Bi;Qingyao Ai;W. Bruce Croft

Open-Retrieval Conversational Question Answering

DOI：
10.1145/3397271.3401110
发表时间：
2020-05
期刊：
Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval
影响因子：
0
作者：
Chen Qu;Liu Yang;Cen Chen;Minghui Qiu;W. Bruce Croft;Mohit Iyyer
通讯作者：
Chen Qu;Liu Yang;Cen Chen;Minghui Qiu;W. Bruce Croft;Mohit Iyyer

Conversational Product Search Based on Negative Feedback

DOI：
10.1145/3357384.3357939
发表时间：
2019-09
期刊：
Proceedings of the 28th ACM International Conference on Information and Knowledge Management
影响因子：
0
作者：
Keping Bi;Qingyao Ai;Yongfeng Zhang;W. Bruce Croft
通讯作者：
Keping Bi;Qingyao Ai;Yongfeng Zhang;W. Bruce Croft

Leverage Implicit Feedback for Context-aware Product Search

DOI：
发表时间：
2019-09
期刊：
ArXiv
影响因子：
0
作者：
Keping Bi;C. Teo;Yesh Dattatreya;Vijai Mohan;W. Bruce Croft
通讯作者：
Keping Bi;C. Teo;Yesh Dattatreya;Vijai Mohan;W. Bruce Croft

Answer Interaction in Non-factoid Question Answering Systems

DOI：
10.1145/3295750.3298946
发表时间：
2019-01
期刊：
Proceedings of the 2019 Conference on Human Information Interaction and Retrieval
影响因子：
0
作者：
Chen Qu;Liu Yang;W. Bruce Croft;Falk Scholer;Yongfeng Zhang
通讯作者：
Chen Qu;Liu Yang;W. Bruce Croft;Falk Scholer;Yongfeng Zhang