Bootstrapping Lexical Choice via Multiple-Sequence Alignment

An important component of any generation system is the mapping dictionary, a lexicon of elementary semantic expressions and corresponding natural language realizations. Typically, labor-intensive knowledge-based methods are used to construct the dictionary. We instead propose to acquire it automatically via a novel multiple-pass algorithm employing multiple-sequence alignment, a technique commonly used in bioinformatics. Crucially, our method leverages latent information contained in multiparallel corpora -- datasets that supply several verbalizations of the corresponding semantics rather than just one. We used our techniques to generate natural language versions of computer-generated mathematical proofs, with good results on both a per-component and overall-output basis. For example, in evaluations involving a dozen human judges, our system produced output whose readability and faithfulness to the semantic input rivaled that of a traditional generation system. Publication info: Proce...

• Type: Journal
• Year: 2002
• Where: CORR
• Authors: Regina Barzilay, Lillian Lee
• Keywords: CORR 2002, Education, Elementary Semantic Expressions, Natural Language, Natural Language Realizations