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 2111.00808cs.CL
收藏

无监督的非作格动词发现

Unsupervised Discovery of Unaccusative and Unergative Verbs

University of Gothenburg(哥德堡大学);University of Edinburgh(爱丁堡大学);Uppsala University(乌普萨拉大学);IT University of Copenhagen(哥本哈根信息技术大学)

Sharid Loáiciga, Luca Bevacqua, Christian Hardmeier

摘要:

我们提出了一种无监督的方法来检测英语非作格和非解释动词。这些范畴使我们能够在不知道动词语义角色的情况下识别出参与使役-始动交替的动词。该方法基于候选动词的不及物句变体的生成和语言模型的探索。我们获得了与类似方法相当的结果,并且不依赖于注释资源。

英文摘要:

We present an unsupervised method to detect English unergative and unaccusative verbs. These categories allow us to identify verbs participating in the causative-inchoative alternation without knowing the semantic roles of the verb. The method is based on the generation of intransitive sentence variants of candidate verbs and probing a language model. We obtained results on par with similar approaches, with the added benefit of not relying on annotated resources.

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。

↑