Learning Japanese-English Bilingual Word Embeddings by Using Language Specificity
Learning Japanese-English Bilingual Word Embeddings by Using Language Specificity
复制标题
利用语言特异性学习日英双语词嵌入
DOI：
10.1142/s2717554520500149
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
and Akira Maeda
中科院分区：
文献类型：
--
作者：
Yuting Song;Biligsaikhan Batjargal;and Akira Maeda
跨语言单词嵌入因为能够捕捉跨语言单词的语义而受到越来越多的关注，这可以应用于跨语言任务。大多数方法学习单个映射(例如，线性映射)以将嵌入空间的单词从一种语言转换为另一种语言。为了改进双语词的嵌入，我们提出了一种改进的方法，该方法增加了特定语言的映射。考虑到日语的特殊性，我们重点学习日英双语词汇嵌入映射。通过与单一的基于映射的日语和英语双语词汇诱导模型的比较，对我们的方法进行了评估。我们确定我们的方法更有效，在日语来源的单词上有显著的改进。
Cross-lingual word embeddings have been gaining attention because they can capture the semantic meaning of words across languages, which can be applied to cross-lingual tasks. Most methods learn a single mapping (e.g., a linear mapping) to transform a word embedding space from one language to another. To improve bilingual word embeddings, we propose an advanced method that adds a language-specific mapping. We focus on learning Japanese-English bilingual word embedding mapping by considering the specificity of the Japanese language. We evaluated our method by comparing it with single mapping-based-models on bilingual lexicon induction between Japanese and English. We determined that our method was more effective, with significant improvements on words of Japanese origin.