arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1809.01682cs.IRcs.CL
收藏

使用增强的文档-查询交互的深度相关性排名

Deep Relevance Ranking Using Enhanced Document-Query Interactions

Athens University of Economics and Business(雅典经济与商业大学);Google AI(谷歌人工智能)

Ryan McDonald, Georgios-Ioannis Brokos, Ion Androutsopoulos

摘要:

我们探索了几种新的文档相关性排名模型,建立在Guo et al.(2016)的深度相关性匹配模型(DRMM)基础上。与DRMM不同,DRMM使用术语的上下文不敏感编码和查询-文档术语交互,我们在整个模型中注入了丰富的上下文敏感编码,灵感来自PACRR(Hui等人,卷积n-gram匹配功能,但以多种方式扩展,包括查询和文档输入的多个视图。我们在来自BIOASQ问答挑战的数据集上测试我们的模型(Tsatsaronis等人,2015年)和TREC ROBUST 2004年(Voorhees,2005年),显示它们优于基于BM 25的基线,DRMM和PACRR。

英文摘要:

We explore several new models for document relevance ranking, building upon the Deep Relevance Matching Model (DRMM) of Guo et al. (2016). Unlike DRMM, which uses context-insensitive encodings of terms and query-document term interactions, we inject rich context-sensitive encodings throughout our models, inspired by PACRR's (Hui et al., 2017) convolutional n-gram matching features, but extended in several ways including multiple views of query and document inputs. We test our models on datasets from the BIOASQ question answering challenge (Tsatsaronis et al., 2015) and TREC ROBUST 2004 (Voorhees, 2005), showing they outperform BM25-based baselines, DRMM, and PACRR.

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。

↑