|
|
Modern Linguistics 2024
自然语言处理视角下日语复合动词的语义计量方法探索——以“V1-あげる”和“V1-あがる”为例
|
Abstract:
本文在自然语言处理视角下，利用Doc2vec句向量工具，以“V1-あげる”、“V1-あがる”为例，就日语复合动词的语义计量方法进行了探索。结果表明，语义分类的平均正确率达90%，利用句向量技术对日语复合动词的语义计量研究具有可行性。同时，对于同一复合动词的多个语义，该工具可为大规模自动判断实际语境中的具体语义提供可靠手段。
From the perspective of natural language processing, this paper uses Doc2vec sentence vector tool and takes “V1-あげる” and “V1-あがる” as examples to explore the semantic measurement of Japanese compound verbs. The results show that the average accuracy of semantic classification is 90%, and it is feasible to use sentence vector technology to study the semantic measurement of Japanese compound verbs. At the same time, for multiple meanings of the same compound verb, the tool can provide a reliable means for large-scale automatic judgment of specific meaning in the actual context.
| [1] | 杨晓敏. 日语复合动词的多义性研究[D]: [博士学位论文]. 上海: 上海外国语大学, 2009. |
| [2] | 森田良行. 基礎日本語1――意味と使い方[M]. 东京: 角川書店, 1997. |
| [3] | Mikolov, T., Sutskever, I., Chen, K., et al. (2013) Distributed Representations of Words and Phrases and Their Compositionality. Advances in Neural Information Processing Systems, 26, 3111-3119. |
| [4] | 唐明, 朱磊, 邹显春. 基于Word2vec的一种文档向量表示[J]. 计算机科学, 2016(6): 214-217 269. |
| [5] | Le, Q.V. and Mikolov, T. (2014) Distributed Representations of Sentences and Documents. arXiv: 1405.4053. |
| [6] | 施建军. 基于词向量的汉日通用汉字词语义计量研究方法探索[J]. 外语教学理论与实践, 2023(1): 18-36. |
| [7] | 姫野昌子. 複合動詞？「~あがる」, 「~あげる」および下降を表す複合動詞類[M]. 东京: ひつじ書房, 1999. |
| [8] | 杨晓敏. 核心图式理论下日语复合动词后项“~上げる”多义性再考[J]. 复旦外国语言文学论丛, 2018(3): 33-41. |
| [9] | Capel, A. (2012) Completing the English Vocabulary Profile: Cl and C2 Vocabulary. English Profile Journal, 3, e1. https://doi.org/10.1017/S2041536212000013 |
| [10] | McCarthy, D., Apidianaki, M. and Erk, K. (2016) Word Sense Clustering and Clusterability. Computational Linguistics, 42, 245-275. https://doi.org/10.1162/COLI_a_00247 |
