- 【Updated on May 12, 2025】 Integration of CiNii Dissertations and CiNii Books into CiNii Research
- Trial version of CiNii Research Automatic Translation feature is available on CiNii Labs
- Suspension and deletion of data provided by Nikkei BP
- Regarding the recording of “Research Data” and “Evidence Data”
Automatic Synonym Acquisition Using a Context-Restricted Skip-gram Model
-
- Joko Hideaki
- Mitsubishi Electric Co., Information Technology R&D Center
-
- Matsuda Yoshitatsu
- Graduate School of Arts and Sciences, the University of Tokyo
-
- Yamaguchi Kazunori
- Graduate School of Arts and Sciences, the University of Tokyo
Bibliographic Information
- Other Title
-
- 文脈限定 Skip-gram による同義語獲得
- ブンミャク ゲンテイ Skip-gram ニ ヨル ドウギゴ カクトク
Search this article
Description
<p>This research proposes a context-restricted Skip-gram model for acquiring synonyms by employing various properties of the context words. The original Skip-gram model learned the word vector of each target word by utilizing all the context words around it. In contrast, the proposed context-restricted Skip-gram model learns multiple word vector types of each target word by limiting the context words to those pertaining to specific parts of speech or those present at specific relative positions. The proposed method calculates the cosine similarities on multiple word vector types and combines these similarities using linear support vector machines. The proposed method has high interpretability because it is a weighted linear summation of simple models. The interpretability of the proposed method enables us to investigate the degree of influence for acquiring synonyms from various properties of the context words. Moreover, the proposed method has high extendability because the conditions of context restriction can be easily changed and added. Experimental results using actual Japanese corpora showed that the proposed method aggregating multiple context-restricted models achieved a higher performance than the previous single Skip-gram model. In addition, the estimated weights of various properties of the context words could appropriately elucidate some grammatical characteristics of the Japanese language. </p>
Journal
-
- Journal of Natural Language Processing
-
Journal of Natural Language Processing 24 (2), 187-204, 2017
The Association for Natural Language Processing
- Tweet
Details 詳細情報について
-
- CRID
- 1390282679453292544
-
- NII Article ID
- 130006832587
-
- NII Book ID
- AN10472659
-
- ISSN
- 21858314
- 13407619
-
- NDL BIB ID
- 028060828
-
- Text Lang
- ja
-
- Article Type
- journal article
-
- Data Source
-
- JaLC
- NDL Search
- Crossref
- CiNii Articles
- KAKEN
- OpenAIRE
-
- Abstract License Flag
- Disallowed