Abstract
Often, Statistical Machine Translation (SMT) between English and Korean suffers from null alignment. Previous studies have attempted to resolve this problem by removing unnecessary function words, or by reordering source sentences. However, the removal of function words can cause a serious loss in information. In this paper, we present a possible method of bridging the morpho-syntactic gap for English-Korean SMT. In particular, the proposed method tries to transform a source sentence by inserting pseudo words, and by reordering the sentence in such a way that both sentences have a similar length and word order. The proposed method achieves 2.4 increase in BLEU score over baseline phrase-based system.
| Original language | English |
|---|---|
| Title of host publication | ACL-IJCNLP 2009 - Joint Conf. of the 47th Annual Meeting of the Association for Computational Linguistics and 4th Int. Joint Conf. on Natural Language Processing of the AFNLP, Proceedings of the Conf. |
| Pages | 233-236 |
| Number of pages | 4 |
| Publication status | Published - 2009 Dec 1 |
| Event | Joint Conference of the 47th Annual Meeting of the Association for Computational Linguistics and 4th International Joint Conference on Natural Language Processing of the AFNLP, ACL-IJCNLP 2009 - Suntec, Singapore Duration: 2009 Aug 2 → 2009 Aug 7 |
Other
| Other | Joint Conference of the 47th Annual Meeting of the Association for Computational Linguistics and 4th International Joint Conference on Natural Language Processing of the AFNLP, ACL-IJCNLP 2009 |
|---|---|
| Country | Singapore |
| City | Suntec |
| Period | 09/8/2 → 09/8/7 |
Fingerprint
ASJC Scopus subject areas
- Language and Linguistics
- Linguistics and Language
Cite this
Hong, G., Lee, S. W., & Rim, H-C. (2009). Bridging morpho-syntactic gap between source and target sentences for English-Korean Statistical Machine Translation. In ACL-IJCNLP 2009 - Joint Conf. of the 47th Annual Meeting of the Association for Computational Linguistics and 4th Int. Joint Conf. on Natural Language Processing of the AFNLP, Proceedings of the Conf. (pp. 233-236)