arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2012.08787cs.IR
收藏

人工生成文本的查询扩展

Query expansion with artificially generated texts

Vincent Claveau

摘要:

一个众所周知的提高文档检索性能的方法是扩展用户的查询。在文献中已经提出了几种方法,其中一些被认为是产生国家的最先进的结果在IR。在本文中,我们探讨了使用文本生成自动扩展查询。我们依赖于一个著名的神经生成模型GPT-2,它带有针对英语的预训练模型,但也可以在特定语料库上进行微调。通过不同的实验,我们表明,文本生成是一个非常有效的方式来提高IR系统的性能,具有很大的利润(+10%MAP增益),它优于强基线也依赖于查询扩展(LM+ RM 3)。由于GPT代码和模型的可用性,这种概念上简单的方法可以很容易地在任何IR系统上实现。

英文摘要:

A well-known way to improve the performance of document retrieval is to expand the user's query. Several approaches have been proposed in the literature, and some of them are considered as yielding state-of-the-art results in IR. In this paper, we explore the use of text generation to automatically expand the queries. We rely on a well-known neural generative model, GPT-2, that comes with pre-trained models for English but can also be fine-tuned on specific corpora. Through different experiments, we show that text generation is a very effective way to improve the performance of an IR system, with a large margin (+10% MAP gains), and that it outperforms strong baselines also relying on query expansion (LM+RM3). This conceptually simple approach can easily be implemented on any IR system thanks to the availability of GPT code and models.

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。

↑