arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2301.09728cs.IR
收藏

将BM25分数作为文本注入可改进基于BERT的重新排序

Injecting the BM25 Score as Text Improves BERT-Based Re-rankers

Arian Askari, Amin Abolghasemi, Gabriella Pasi, Wessel Kraaij, Suzan Verberne

摘要:

在本文中,我们提出了一种新的方法相结合的第一阶段的词汇检索模型和基于transformer的重排序:我们注入的词汇模型的相关性得分作为一个令牌在中间的输入的跨编码器重排序。先前的研究表明,词汇和BERT重排序器的相关性得分之间的插值可能不会始终导致更高的有效性。我们的想法是由发现BERT模型可以捕捉数值信息的动机。我们比较了几种表示的BM 25分数,并将它们作为文本注入四个不同的交叉编码器的输入。我们还分析了不同的查询类型的效果,并调查我们的方法捕获精确匹配的相关性的有效性。对MSMARCO Passage集合和TREC DL集合的评估表明,所提出的方法显着改善了所有交叉编码器重排序以及常见的插值方法。我们表明,改进是一致的所有查询类型。我们还发现,在BM25和交叉编码器的精确匹配能力的改进。我们的研究结果表明,交叉编码器重排序器可以有效地提高没有额外的计算负担和额外的步骤,在管道中显式地添加第一阶段的排名器的输出到模型输入,这种效果是强大的不同的模型和查询类型。

英文摘要:

In this paper we propose a novel approach for combining first-stage lexical retrieval models and Transformer-based re-rankers: we inject the relevance score of the lexical model as a token in the middle of the input of the cross-encoder re-ranker. It was shown in prior work that interpolation between the relevance score of lexical and BERT-based re-rankers may not consistently result in higher effectiveness. Our idea is motivated by the finding that BERT models can capture numeric information. We compare several representations of the BM25 score and inject them as text in the input of four different cross-encoders. We additionally analyze the effect for different query types, and investigate the effectiveness of our method for capturing exact matching relevance. Evaluation on the MSMARCO Passage collection and the TREC DL collections shows that the proposed method significantly improves over all cross-encoder re-rankers as well as the common interpolation methods. We show that the improvement is consistent for all query types. We also find an improvement in exact matching capabilities over both BM25 and the cross-encoders. Our findings indicate that cross-encoder re-rankers can efficiently be improved without additional computational burden and extra steps in the pipeline by explicitly adding the output of the first-stage ranker to the model input, and this effect is robust for different models and query types.

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。

↑