arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.04667cs.IRcs.CLcs.LG
收藏

QueryBuilder:面向信息检索的人在回路查询开发

QueryBuilder: Human-in-the-Loop Query Development for Information Retrieval

Raytheon BBN Technologies(雷神BBN技术公司);University of Massachusetts, Amherst(马萨诸塞大学阿默斯特分校);National Institute of Standards and Technology(美国国家标准与技术研究院);Amazon AWS AI Labs(亚马逊AWS AI实验室)

Hemanth Kandula, Damianos Karakos, Haoling Qiu, Benjamin Rozonoyer, Ian Soboroff, Lee Tarlin, Bonan Min

AI总结:

本文提出交互式人在回路系统 QueryBuilder,通过近实时检索、句子相关性标注、查询词与事件特征加权及神经检索迭代细化,帮助新手低成本构建跨语言细粒度查询。

摘要:

信息检索(IR)系统的用户通常从一个总体信息需求(即分析任务)出发,进而定义更细粒度的查询,以覆盖该分析任务的各个重要方面(即子主题)。我们提出了一种名为 QueryBuilder 的新型交互式系统,它使说英语的新手用户能够以少量精力创建查询,方法是高效探索英文开发语料库,从而快速开发出与其信息需求相对应的跨语言信息检索查询。QueryBuilder 根据用户输入的检索词进行近实时文档检索;用户浏览检索到的文档,并将与所需信息相关的句子标记为相关。系统将标记的句子用作查询形成和细化中的附加信息:对查询词(以及可选的事件特征,这些特征捕获事件“触发词”(指示词)和施事/受事角色)进行适当加权,并由一个能更好捕获文本含义的基于神经的系统检索其他相关内容。检索和标记过程可根据需要重复多次,从而在每次迭代中产生越来越精细的查询。最终产物是用于跨语言信息检索(CLIR)的细粒度查询。我们使用 IARPA BETTER IR 数据集中的分析任务和请求进行的实验表明,只需少量精力(每个子主题最多10分钟),新手用户即可形成有用的细粒度查询,包括使用他们不懂的语言。QueryBuilder 还为传统的语料库探索和查询形成过程提供了有益能力。演示视频发布于 https://vimeo.com/734795835

英文摘要:

Frequently, users of an Information Retrieval (IR) system start with an overarching information need (a.k.a., an analytic task) and proceed to define finer-grained queries covering various important aspects (i.e., sub-topics) of that analytic task. We present a novel, interactive system called $\textit{QueryBuilder}$, which allows a novice, English-speaking user to create queries with a small amount of effort, through efficient exploration of an English development corpus in order to rapidly develop cross-lingual information retrieval queries corresponding to the user's information needs. QueryBuilder performs near real-time retrieval of documents based on user-entered search terms; the user looks through the retrieved documents and marks sentences as relevant to the information needed. The marked sentences are used by the system as additional information in query formation and refinement: query terms (and, optionally, event features, which capture event $'triggers'$ (indicator terms) and agent/patient roles) are appropriately weighted, and a neural-based system, which better captures textual meaning, retrieves other relevant content. The process of retrieval and marking is repeated as many times as desired, giving rise to increasingly refined queries in each iteration. The final product is a fine-grained query used in Cross-Lingual Information Retrieval (CLIR). Our experiments using analytic tasks and requests from the IARPA BETTER IR datasets show that with a small amount of effort (at most 10 minutes per sub-topic), novice users can form $\textit{useful}$ fine-grained queries including in languages they don't understand. QueryBuilder also provides beneficial capabilities to the traditional corpus exploration and query formation process. A demonstration video is released at https://vimeo.com/734795835

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。

↑