Multi-align: Combining Linguistic and Statistical Techniques to Improve Alignments for Adaptable MT

Abstract. An adaptable statistical or hybrid MT system relies heavily on the quality of word-level alignments of real-world data. Statistical alignment approaches provide a reasonable initial estimate for word alignment. However, they cannot handle certain types of linguistic phenomena such as long-distance dependencies and structural differences between languages. We address this issue in Multi-Align, a new framework for incremental testing of different alignment algorithms and their combinations. Our design allows users to tune their systems to the properties of a particular genre/domain while still benefiting from general linguistic knowledge associated with a language pair. We demonstrate that a combination of statistical and linguistically-informed alignments can resolve translation divergences during the alignment process.

• Type: Conference
• Year: 2004
• Where: AMTA
• Authors: Necip Fazil Ayan, Bonnie J. Dorr, Nizar Habash
• Keywords: AMTA 2004, Different Alignment Algorithms, Information Management, Statistical Alignment, Word Alignment