What types of word alignment improve statistical machine translation?
- 470 Downloads
In most statistical machine translation (SMT) systems, bilingual segments are extracted via word alignment. However, there is a need for systematic study as to what alignment characteristics can benefit MT under specific experimental settings such as the type of MT system, the language pair or the type or size of the corpus. In this paper we perform, in each of these experimental settings, a statistical analysis of the data and study the sample correlation coefficients between a number of alignment or phrase table characteristics and variables such as the phrase table size, the number of untranslated words or the BLEU score. We report results for two different SMT systems (a phrase-based and an n-gram-based system) on Chinese-to-English FBIS and BTEC data, and Spanish-to-English European Parliament data. We find that the alignment characteristics which help in translation greatly depend on the MT system and on the corpus size. We give alignment hints to improve BLEU score, depending on the SMT system used and the type of corpus. For example, for phrase-based SMT, dense alignments are required with larger corpora, especially on the target side, while with smaller corpora, more precise, sparser alignments are better, especially on the source side. Avoiding some long-distance crossing links may also improve BLEU score with small corpora. We take these conclusions into account to modify two types of alignment systems, and get 1 to 1.6 % relative improvements in BLEU score on two held-out corpora, although the improved system is different in each corpus.
KeywordsStatistical machine translation Word alignment Phrase extraction Discriminative training
Unable to display preview. Download preview PDF.
- Ayan NF, Dorr BJ (2006) Going beyond AER: an extensive analysis of word alignments and their impact on MT. In: Proceedings of the 21st international conference on computational linguistics and 44th annual meeting of the association for computational linguistics. Sydney, Australia, pp 9–16Google Scholar
- Brown PF, Della Pietra SA, Della Pietra VJ, Mercer RL (1993) The mathematics of statistical machine translation: parameter estimation. Comput Linguist 19(2): 263–311Google Scholar
- Chen B, Federico M (2006) Improving phrase-based statistical translation through combination of word alignment. In: Proceedings of FinTAL—5th international conference on natural language processing. Turku, Finland, pp 356–367Google Scholar
- Clark JH, Dyer C, Lavie A, Smith NA (2011) Better hypothesis testing for statistical machine translation: controlling for optimizer instability. In: Proceedings of the 49th annual meeting of the association for computational linguistics. Portland, Oregon, USA, pp 176–181Google Scholar
- DeNero J, Klein D (2007) Tailoring word alignments to syntactic machine translation. In: Proceedings of the 45th annual meeting of the association for computational linguistics. Prague, Czech Republic, pp 17–24Google Scholar
- Guzman F, Gao Q, Vogel S (2009) Reassessment of the role of phrase extraction in PBSMT. In: Proceedings of machine translation summit XII. Ottawa, Canada, pp 49–56Google Scholar
- Koehn P, Och FJ, Marcu D (2003) Statistical phrase-based translation. In: Proceedings of the human language technology conference of the NAACL. Edmonton, Canada, pp 48–54Google Scholar
- Koehn P, Hoang H, Birch A, Callison-Burch C, Federico M, Bertoldi N, Cowan B, Shen W, Moran C, Zens R, Dyer C, Bojar O, Constantin A, Herbst E (2007) Moses: open source toolkit for statistical machine translation. In: Proceedings of the 45th annual meeting of the association for computational linguistics (demo and poster sessions). Association for Computational Linguistics, Prague, Czech Republic, pp 177–180Google Scholar
- Lambert P, Banchs RE (2006) Tuning machine translation parameters with SPSA. In: Proceedings of the international workshop on spoken language translation, IWSLT’06. Kyoto, Japan, pp 190–196Google Scholar
- Lambert P, Banchs RE (2011) BIA: a discriminative phrase alignment toolkit. Prague Bulletin of Mathematical Linguistics 97Google Scholar
- Lambert P, Banchs RE, Crego JM (2007) Discriminative alignment training without annotated data for machine translation. In: Proceedings of the human language technology conference of the NAACL (short papers). Rochester, NY, USA, pp 85–88Google Scholar
- Lambert P, Ma Y, Ozdowska S, Way A (2009) Tracking relevant alignment characteristics for machine translation. In: Proceedings of machine translation summit XII. Ottawa, Canada, pp 268–275Google Scholar
- Liang P, Taskar B, Klein D (2006) Alignment by agreement. In: Proceedings of the human language technology conference of the NAACL. New York City, USA, pp 104–111Google Scholar
- Moore RC (2005) A discriminative framework for bilingual word alignment. In: Proceedings of human language technology conference and conference on empirical methods in natural language processing. Vancouver, Canada, pp 81–88Google Scholar
- Och FJ (2003) Minimum error rate training in statistical machine translation. In: Proceedings of the 41th annual meeting of the association for computational linguistics, pp 160–167Google Scholar
- Papineni K, Roukos S, Ward T, Zhu W-J (2002) Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th annual meeting of the association for computational linguistics. Philadelphia, USA, pp 311–318Google Scholar
- Spall JC (1998) An overview of the simultaneous perturbation method for efficient optimization. Johns Hopkins APL Techn Digest 19(4): 482–492Google Scholar
- Takezawa T, Sumita E, Sugaya F, Yamamoto H, Yamamoto S (2002) Toward a broad-coverage bilingual corpus for speech translation of travel conversations in the real world. In: Proceedings of third international conference on language resources and evaluation 2002. Las Palmas, Canary Islands, Spain, pp 147–152Google Scholar
- Vilar D, Popovic M, Ney H (2006) AER: do we need to “improve” our alignments? In: Proceedings of the international workshop on spoken language translation, IWSLT’06. Kyoto, Japan, pp 205–212Google Scholar