俄语形态嵌入的评价

V. Romanov, A. Khusainova
{"title":"俄语形态嵌入的评价","authors":"V. Romanov, A. Khusainova","doi":"10.1145/3342827.3342846","DOIUrl":null,"url":null,"abstract":"A number of morphology-based word embedding models were introduced in recent years. However, their evaluation was mostly limited to English, which is known to be a morphologically simple language. In this paper, we explore whether and to what extent incorporating morphology into word embeddings improves performance on downstream NLP tasks, in the case of morphologically rich Russian language. NLP tasks of our choice are POS tagging, Chunking, and NER -- for Russian language, all can be mostly solved using only morphology without understanding the semantics of words. Our experiments show that morphology-based embeddings trained with Skipgram objective do not outperform existing embedding model -- FastText. Moreover, a more complex, but morphology unaware model, BERT, allows to achieve significantly greater performance on the tasks that presumably require understanding of a word's morphology.","PeriodicalId":254461,"journal":{"name":"Proceedings of the 2019 3rd International Conference on Natural Language Processing and Information Retrieval","volume":"12 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Evaluation of Morphological Embeddings for the Russian Language\",\"authors\":\"V. Romanov, A. Khusainova\",\"doi\":\"10.1145/3342827.3342846\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"A number of morphology-based word embedding models were introduced in recent years. However, their evaluation was mostly limited to English, which is known to be a morphologically simple language. In this paper, we explore whether and to what extent incorporating morphology into word embeddings improves performance on downstream NLP tasks, in the case of morphologically rich Russian language. NLP tasks of our choice are POS tagging, Chunking, and NER -- for Russian language, all can be mostly solved using only morphology without understanding the semantics of words. Our experiments show that morphology-based embeddings trained with Skipgram objective do not outperform existing embedding model -- FastText. Moreover, a more complex, but morphology unaware model, BERT, allows to achieve significantly greater performance on the tasks that presumably require understanding of a word's morphology.\",\"PeriodicalId\":254461,\"journal\":{\"name\":\"Proceedings of the 2019 3rd International Conference on Natural Language Processing and Information Retrieval\",\"volume\":\"12 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2019-06-28\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the 2019 3rd International Conference on Natural Language Processing and Information Retrieval\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/3342827.3342846\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 2019 3rd International Conference on Natural Language Processing and Information Retrieval","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3342827.3342846","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

摘要

近年来提出了许多基于词法的词嵌入模型。然而,他们的评价大多局限于英语,这是一种已知的形态简单的语言。在本文中,我们探讨了在形态学丰富的俄语的情况下,将形态学纳入词嵌入是否以及在多大程度上提高了下游NLP任务的性能。我们选择的NLP任务是词性标注、分块和NER——对于俄语来说,所有这些任务都可以只用形态学来解决,而不需要理解单词的语义。我们的实验表明,使用Skipgram目标训练的基于形态学的嵌入并不优于现有的嵌入模型——FastText。此外,一个更复杂但不知道词法的模型BERT,可以在可能需要理解单词词法的任务上取得显著更好的性能。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Evaluation of Morphological Embeddings for the Russian Language
A number of morphology-based word embedding models were introduced in recent years. However, their evaluation was mostly limited to English, which is known to be a morphologically simple language. In this paper, we explore whether and to what extent incorporating morphology into word embeddings improves performance on downstream NLP tasks, in the case of morphologically rich Russian language. NLP tasks of our choice are POS tagging, Chunking, and NER -- for Russian language, all can be mostly solved using only morphology without understanding the semantics of words. Our experiments show that morphology-based embeddings trained with Skipgram objective do not outperform existing embedding model -- FastText. Moreover, a more complex, but morphology unaware model, BERT, allows to achieve significantly greater performance on the tasks that presumably require understanding of a word's morphology.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信