arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.14541cs.IRcs.CL
收藏

面向学术论文相似度分析的专业化文档嵌入

Specialized Document Embeddings for Aspect-based Similarity of Research Papers

DFKI GmbH(德国人工智能研究中心);Ernst & Young GmbH WPG(安永会计师事务所(德国));University of Wuppertal(伍珀塔尔大学);University of Göttingen(哥廷根大学)

Malte Ostendorff, Till Blume, Terry Ruas, Bela Gipp, Georg Rehm

摘要:

文档嵌入和相似性度量支持基于内容的推荐系统,其中文档通常表示为单个通用嵌入。然而,在单个向量表示上计算的相似性仅提供了关于文档相似性的一个视角,忽略了哪些方面使两个文档相似。为了解决这一限制,已经开发了基于方面的相似性措施,使用文档分割或成对多类文档分类。虽然分割损害了文档的连贯性,但成对分类方法对大规模语料库的扩展性很差。在本文中,我们把基于方面的相似性作为一个经典的向量相似性问题,在特定方面的嵌入空间。我们不是将文档表示为单个通用嵌入,而是表示为多个专用嵌入。我们的方法避免了文件分割和规模线性w.r.t.语料库的大小。在实证研究中,我们使用包含157,606篇研究论文的Papers with Code语料库,并将各自研究论文的任务,方法和数据集作为其方面。我们比较和分析三个通用的文档嵌入,六个专门的文档嵌入和成对的分类基线的背景下,研究论文的建议。作为通用文档嵌入,我们考虑FastText,SciBERT和SPECTER。为了计算专门的文档嵌入,我们比较了三种替代方法,灵感来自改造,微调和暹罗网络。在我们的实验中,Siamese SciBERT获得了最高的分数。额外的分析表明,对数据集方面和对每个研究论文的方法方面的通用文档嵌入的隐含偏见。我们的方法基于方面的文档嵌入减轻潜在的风险所产生的隐性偏见,使他们明确。

英文摘要:

Document embeddings and similarity measures underpin content-based recommender systems, whereby a document is commonly represented as a single generic embedding. However, similarity computed on single vector representations provides only one perspective on document similarity that ignores which aspects make two documents alike. To address this limitation, aspect-based similarity measures have been developed using document segmentation or pairwise multi-class document classification. While segmentation harms the document coherence, the pairwise classification approach scales poorly to large scale corpora. In this paper, we treat aspect-based similarity as a classical vector similarity problem in aspect-specific embedding spaces. We represent a document not as a single generic embedding but as multiple specialized embeddings. Our approach avoids document segmentation and scales linearly w.r.t.the corpus size. In an empirical study, we use the Papers with Code corpus containing 157,606 research papers and consider the task, method, and dataset of the respective research papers as their aspects. We compare and analyze three generic document embeddings, six specialized document embeddings and a pairwise classification baseline in the context of research paper recommendations. As generic document embeddings, we consider FastText, SciBERT, and SPECTER. To compute the specialized document embeddings, we compare three alternative methods inspired by retrofitting, fine-tuning, and Siamese networks. In our experiments, Siamese SciBERT achieved the highest scores. Additional analyses indicate an implicit bias of the generic document embeddings towards the dataset aspect and against the method aspect of each research paper. Our approach of aspect-based document embeddings mitigates potential risks arising from implicit biases by making them explicit.

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。

↑