arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2103.00854cs.CL
收藏

Vyākarana:一个无色绿色的印度语句法评测基准

Vyākarana: A Colorless Green Benchmark for Syntactic Evaluation in Indic Languages

BITS Pilani, Goa Campus(贝拉理工学院果阿校区);Columbia University(哥伦比亚大学);PICT(浦那工程与技术学院)

Rajaswa Patil, Jasleen Dhillon, Siddhant Mahurkar, Saumitra Kulkarni, Manav Malhotra, Veeky Baths

摘要:

虽然在为印度语言开发自然语言理解资源方面取得了重大进展,但句法评估相对较少。与英语不同,印度语有丰富的形态句法,语法性别,自由的线性词序和高度曲折的形态。在本文中,我们介绍Vyākarana:一个基准的无色绿色句子在印度语言的多语种语言模型的句法评估。该基准测试包括四个与语法相关的任务:PoS标记、语义树深度预测、语法格标记和主谓一致。我们使用的数据集的评估任务,以探讨五种多语言的语言模型的不同架构的语法在印度语言。由于其普遍性,我们也包括在我们的实验中的代码转换设置。我们的研究结果表明,从印度语言模型(IndicBERT和MuRIL)的标记级和标记级表示不捕捉印度语言的语法,有效地作为其他高度多语言的语言模型。此外,我们的逐层探测实验表明,虽然mBERT,DistilmBERT和XLM-R本地化的语法在中间层,印度语言模型不显示这样的语法本地化。

英文摘要:

While there has been significant progress towards developing NLU resources for Indic languages, syntactic evaluation has been relatively less explored. Unlike English, Indic languages have rich morphosyntax, grammatical genders, free linear word-order, and highly inflectional morphology. In this paper, we introduce Vyākarana: a benchmark of Colorless Green sentences in Indic languages for syntactic evaluation of multilingual language models. The benchmark comprises four syntax-related tasks: PoS Tagging, Syntax Tree-depth Prediction, Grammatical Case Marking, and Subject-Verb Agreement. We use the datasets from the evaluation tasks to probe five multilingual language models of varying architectures for syntax in Indic languages. Due to its prevalence, we also include a code-switching setting in our experiments. Our results show that the token-level and sentence-level representations from the Indic language models (IndicBERT and MuRIL) do not capture the syntax in Indic languages as efficiently as the other highly multilingual language models. Further, our layer-wise probing experiments reveal that while mBERT, DistilmBERT, and XLM-R localize the syntax in middle layers, the Indic language models do not show such syntactic localization.

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。

↑