arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.00876cs.CLcs.AI
收藏

词序与世界知识

Word Order and World Knowledge

Beihang University(北京航空航天大学);University of Copenhagen(哥本哈根大学)

Qinghua Zhao, Vinit Ravishankar, Nicolas Garneau, Anders Søgaard

AI总结:

本文通过五种语言、六种固定词序的文本预训练语言模型,并用词语类比探测词序对世界知识归纳的影响,发现固定词序表现存在稳定差异,而Wov2Lex假设不成立。

摘要:

词序是自然语言中的一个重要概念,在本研究中,我们研究词序如何影响使用语言模型从原始文本中归纳世界知识。我们使用词语类比来探测此类知识。具体而言,除自然词序外,我们首先从五种语言中分别提取六种固定词序的文本,然后在这些文本上预训练语言模型。最后,我们分析固定词序在词语类比上的实验结果,并表明:i)某些固定词序始终优于或劣于其他词序,尽管具体情况因语言而异;ii)Wov2Lex假设在预训练语言模型中并不成立,且自然词序通常产生平庸的结果。源代码将在 https://github.com/lshowway/probing_by_analogy 公开发布。

英文摘要:

Word order is an important concept in natural language, and in this work, we study how word order affects the induction of world knowledge from raw text using language models. We use word analogies to probe for such knowledge. Specifically, in addition to the natural word order, we first respectively extract texts of six fixed word orders from five languages and then pretrain the language models on these texts. Finally, we analyze the experimental results of the fixed word orders on word analogies and show that i) certain fixed word orders consistently outperform or underperform others, though the specifics vary across languages, and ii) the Wov2Lex hypothesis is not hold in pre-trained language models, and the natural word order typically yields mediocre results. The source code will be made publicly available at https://github.com/lshowway/probing_by_analogy.

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。

↑