arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2301.08115cs.CL
收藏

语言嵌入有时包含类型学概括

Language Embeddings Sometimes Contain Typological Generalizations

Stockholm University(斯德哥尔摩大学)

Robert Östling, Murathan Kurfalı

摘要:

神经网络模型能在多大程度上学习关于语言结构的概括,我们如何发现它们学到了什么?我们通过在1295种语言的圣经翻译的大规模多语言数据集上训练一系列自然语言处理任务的神经模型来探索这些问题。然后,将学习到的语言表示与现有的类型学数据库以及通过注释投影获得的一组新的定量句法和形态特征进行比较。我们的结论是,一些概括是令人惊讶的接近传统的功能,从语言类型学,但我们的大多数模型,以及以前的工作,似乎并没有作出有意义的语言概括。仔细注意评估中的细节对于避免误报至关重要。此外,为了鼓励在这一领域的持续工作,我们发布了几个资源,涵盖了我们数据中的大多数或所有语言:(i)多套语言表示,(ii)多语言词嵌入,(iii)预测和预测的句法和形态特征,(iv)提供语言表示的语言学合理评估的软件。

英文摘要:

To what extent can neural network models learn generalizations about language structure, and how do we find out what they have learned? We explore these questions by training neural models for a range of natural language processing tasks on a massively multilingual dataset of Bible translations in 1295 languages. The learned language representations are then compared to existing typological databases as well as to a novel set of quantitative syntactic and morphological features obtained through annotation projection. We conclude that some generalizations are surprisingly close to traditional features from linguistic typology, but that most of our models, as well as those of previous work, do not appear to have made linguistically meaningful generalizations. Careful attention to details in the evaluation turns out to be essential to avoid false positives. Furthermore, to encourage continued work in this field, we release several resources covering most or all of the languages in our data: (i) multiple sets of language representations, (ii) multilingual word embeddings, (iii) projected and predicted syntactic and morphological features, (iv) software to provide linguistically sound evaluations of language representations.

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。

↑