Applying Semantic Similarity to Phrase Pivot Translation

• Published in: 2016 IEEE 28th International Conference on Tools with Artificial Intelligence (ICTAI) pp. 1043 - 1047
• Main Authors: Hai-Long Trieu, Le-Minh Nguyen
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01-11-2016
• Subjects: Bridges; Data mining; Pragmatics; Semantics; Testing; Training; Tuning
• ISSN: 2375-0197
• DOI: 10.1109/ICTAI.2016.0160

Pivot methods have shown to be an effective solution to overcome the problem of unavailable large bilingual corpora in statistical machine translation. The representative approach of pivot methods is the phrase pivot translation which is based on common pivot phrases to produce connections between source-pivot and pivot-target phrase tables. Nevertheless, this approach produces insufficient connections behind the phrase tables because pivot phrases still contain the same meaning even when they are not matched to each other. In this work, we propose applying semantic similarity between pivot phrases to phrase pivot translation. In order to extract similar pivot phrases, we used string similarity measures for phrase similarity, and WordNet and Word2Vec were used for word similarity. The experiments show that using semantic similarity is able to extract more informative phrases, which can support for phrase pivot translation.