https://scholars.lib.ntu.edu.tw/handle/123456789/413071
標題: | Learning English¡VChinese bilingual word representations from sentence-aligned parallel corpus | 作者: | Yen A.-Z. Huang H.-H. Chen H.-H. |
關鍵字: | Cross-lingual applications;Distributed word representation;Word alignment | 公開日期: | 2019 | 卷: | 56 | 起(迄)頁: | 52-72 | 來源出版物: | Computer Speech and Language | 摘要: | Representation of words in different languages is fundamental for various cross-lingual applications. In the past researches, there was an argument in using or not using word alignment in learning bilingual word representations. This paper presents a comprehensive empirical study on the uses of parallel corpus to learn the word representations in the embedding space. Various non-alignment and alignment approaches are explored to formulate the contexts for Skip-gram modeling. In the approaches without word alignment, concatenating A and B, concatenating B and A, interleaving A with B, shuffling A and B, and using A and B separately are considered, where A and B denote parallel sentences in two languages. In the approaches with word alignment, three word alignment tools, including GIZA++, TsinghuaAligner, and fast_align, are employed to align words in sentences A and B. The effects of alignment direction from A to B or from B to A are also discussed. To deal with the unaligned words in the word alignment approach, two alternatives, using the words aligned with their immediate neighbors and using the words in the interleaving approach, are explored. We evaluate the performance of the adopted approaches in four tasks, including bilingual dictionary induction, cross-lingual information retrieval, cross-lingual analogy reasoning, and cross-lingual word semantic relatedness. These tasks cover the issues of translation, reasoning, and information access. Experimental results show the word alignment approach with conditional interleaving achieves the best performance in most of the tasks. ? 2019 Elsevier Ltd |
URI: | https://scholars.lib.ntu.edu.tw/handle/123456789/413071 | ISSN: | 08852308 | DOI: | 10.1016/j.csl.2019.01.002 |
顯示於: | 資訊工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。