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 2007.04070cs.CL
收藏

基于神经文本表征的引文推荐

Learning Neural Textual Representations for Citation Recommendation

University of Technology Sydney(悉尼科技大学);VNU University of Engineering and Technology, Vietnam National University, Hanoi(河内越南国家大学工程技术大学);Rozetta Institute(Rozetta研究所)

Binh Thanh Kieu, Inigo Jauregi Unanue, Son Bao Pham, Hieu Xuan Phan, Massimo Piccardi

摘要:

随着科学文献的快速增长,手动为论文选择合适的引文变得越来越具有挑战性和耗时。虽然近年来已经提出了几种自动引文推荐方法,但有效的引文推荐文档表示在很大程度上仍然是难以捉摸的。出于这个原因,在本文中,我们提出了一种新的引用推荐方法,该方法利用了文档的深度顺序表示(Sentence-BERT),并在子模块评分函数中级联了Siamese和三重网络。据我们所知,这是第一种将深度表示和子模块选择结合起来用于引文推荐任务的方法。实验使用流行的基准数据集-ACL Anthology Network语料库进行,并使用MRR和F1-at-k得分等指标对基线和最先进的方法进行评估。结果表明,该方法已经能够优于所有的比较方法在每一个测量指标。

英文摘要:

With the rapid growth of the scientific literature, manually selecting appropriate citations for a paper is becoming increasingly challenging and time-consuming. While several approaches for automated citation recommendation have been proposed in the recent years, effective document representations for citation recommendation are still elusive to a large extent. For this reason, in this paper we propose a novel approach to citation recommendation which leverages a deep sequential representation of the documents (Sentence-BERT) cascaded with Siamese and triplet networks in a submodular scoring function. To the best of our knowledge, this is the first approach to combine deep representations and submodular selection for a task of citation recommendation. Experiments have been carried out using a popular benchmark dataset - the ACL Anthology Network corpus - and evaluated against baselines and a state-of-the-art approach using metrics such as the MRR and F1-at-k score. The results show that the proposed approach has been able to outperform all the compared approaches in every measured metric.

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。

↑