Using Log-linear Models for Selecting Best Machine Translation Output

Michael Carl

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review


We describe a set of experiments to explore statistical techniques for ranking and selecting the best translations in a graph of translation hypotheses. In a previous paper (Carl, 2007) we have described how the hypotheses graph is generated through shallow mapping and permutation rules . We have given examples of its
nodes consisting of vectors representing morpho-syntactic properties of words and phrases. This paper describes a number of methods for elaborating statistical feature functions from some of the vector components. The feature functions are trained off-line on different types of text and their log-linear combination is then used to retrieve the best translation paths in the graph. We compare two language modelling toolkits, the CMU and the SRI toolkit and arrive at three results: 1) word-lemma based feature function models produce better results than token-based models, 2) adding a PoS-tag feature function to the word-lemma model improves the output and 3) weights for lexical translations are suitable if the training material is similar to the texts to be translated.
Original languageEnglish
Title of host publicationThe LREC 2008 Proceedings : The Sixth International Conference on Language Resources and Evaluation (LREC'08)
EditorsNicoletta Calzolari, Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odijk, Stelios Piperidis, Daniel Tapias
Number of pages8
Place of PublicationParis
PublisherEuropean Language Resources Association
Publication date2008
ISBN (Print)2951740840
Publication statusPublished - 2008
Externally publishedYes
EventThe 6th International Conference on Language Resources and Evaluation. LREC 2008 - Marrakech, Morocco
Duration: 28 May 200830 May 2008
Conference number: 6


ConferenceThe 6th International Conference on Language Resources and Evaluation. LREC 2008
Internet address

Cite this