Improving Statistical Word Alignments with Morpho-syntactic Transformations

Abstract. This paper presents a wide range of statistical word alignment experiments incorporating morphosyntactic information. By means of parallel corpus transformations according to information of POS-tagging, lemmatization or stemming, we explore which linguistic information helps improve alignment error rates. For this, evaluation against a human word alignment reference is performed, aiming at an improved machine translation training scheme which eventually leads to improved SMT performance. Experiments are carried out in a Spanish

• Type: Conference
• Year: 2006
• Where: FINTAL
• Authors: Adrià de Gispert, Deepa Gupta, Maja Popovic, Patrik Lambert, José B. Mariño, Marcello Federico, Hermann Ney, Rafael E. Banchs
• Keywords: FINTAL 2006, Morphosyntactic Information, Natural Language Processing, Parallel Corpus, Word Alignment