Getting the Structure Right for Word Alignment: LEAF

Word alignment is the problem of annotating parallel text with translational correspondence. Previous generative word alignment models have made structural assumptions such as the 1-to-1, 1-to-N, or phrase-based consecutive word assumptions, while previous discriminative models have either made such an assumption directly or used features derived from a generative model making one of these assumptions. We present a new generative alignment model which avoids these structural limitations, and show that it is effective when trained using both unsupervised and semi-supervised training methods.

• Type: Conference
• Year: 2007
• Where: EMNLP
• Authors: Alexander Fraser, Daniel Marcu
• Keywords: Consecutive Word Assumptions, EMNLP 2007, Generative Word Alignment, Natural Language Processing, Word Alignment