Inferring Syntactic Rules for Word Alignment through Inductive Logic Programming

This paper presents and evaluates an original approach to automatically align bitexts at the word level. It relies on a syntactic dependency analysis of the source and target texts and uses a machine-learning technique, namely inductive logic programming, to automatically infer rules called syntactic alignment rules. These rules make the most of the syntactic information to align words. This machine learning approach is entirely automatic, requires a very small amount of training data, and its performance rivals some of the best existing alignment systems. Moreover, syntactic isomorphisms between the source language and the target language are easily identified through the inferred rules.

• Type: Conference
• Year: 2010
• Where: LREC
• Authors: Sylwia Ozdowska, Vincent Claveau
• Keywords: Education, LREC 2010, Syntactic Alignment Rules, Syntactic Dependency Analysis, Syntactic Isomorphisms