arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.08123cs.CLcs.IR
收藏

多语言新闻流的批量聚类

Batch Clustering for Multilingual News Streaming

BNP Paribas AI(法国巴黎银行人工智能部门)

Mathis Linger, Mhamed Hajaiej

摘要:

如今,数字新闻文章被广泛使用,由各种编辑发布,并且通常以不同的语言编写。这种大量的、多样的、无组织的信息使人类阅读变得非常困难,甚至几乎不可能。这导致需要能够将大量多语言新闻安排到故事中的算法。为此,我们扩展了以前的工作主题检测和跟踪,并提出了一个新的系统的灵感来自newsLens。我们每批处理文章,寻找单语本地主题,然后跨时间和语言链接。在这里,我们介绍了一种新颖的“重播”策略,将单语本地主题链接到故事中。此外,我们提出了新的微调多语言嵌入使用SBERT创建跨语言的故事。我们的系统给出了西班牙语和德语新闻数据集上的单语最先进的结果,以及英语,西班牙语和德语新闻的跨语言最先进的结果。

英文摘要:

Nowadays, digital news articles are widely available, published by various editors and often written in different languages. This large volume of diverse and unorganized information makes human reading very difficult or almost impossible. This leads to a need for algorithms able to arrange high amount of multilingual news into stories. To this purpose, we extend previous works on Topic Detection and Tracking, and propose a new system inspired from newsLens. We process articles per batch, looking for monolingual local topics which are then linked across time and languages. Here, we introduce a novel "replaying" strategy to link monolingual local topics into stories. Besides, we propose new fine tuned multilingual embedding using SBERT to create crosslingual stories. Our system gives monolingual state-of-the-art results on dataset of Spanish and German news and crosslingual state-of-the-art results on English, Spanish and German news.

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。

↑