Word Ordering with Phrase-Based Grammars

Word Ordering with Phrase-Based Grammars” by Adrià de Gispert, Marcus Tomalin, and Bill Byrne. In Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics, (Gothenburg, Sweden), Apr. 2014, pp. 259-268 (12 pages).

Abstract

We describe an approach to word ordering using modelling techniques from statistical machine translation. The system incorporates a phrase-based model of string generation that aims to take unordered bags of words and produce fluent, grammatical sentences. We describe the generation grammars and introduce parsing procedures that address the computational complexity of generation under permutation of phrases. Against the best previous results reported on this task, obtained using syntax driven models, we report huge quality improvements, with BLEU score gains of 20+ which we confirm with human fluency judgements. Our system incorporates dependency language models, large n-gram language models, and minimum Bayes risk decoding.

BibTeX entry:

@inproceedings{degispert-tomalin-byrne:2014:EACL,
   author = {Adri{\`a} de Gispert and Marcus Tomalin and Bill Byrne},
   title = {Word Ordering with Phrase-Based Grammars},
   booktitle = {Proceedings of the 14th Conference of the European Chapter
	of the Association for Computational Linguistics},
   pages = {259--268 (12 pages)},
   publisher = {Association for Computational Linguistics},
   address = {Gothenburg, Sweden},
   month = apr,
   year = {2014},
   url = {http://www.aclweb.org/anthology/E14-1028}
}

Back to Bill Byrne publications.