University of Cambridge > Talks.cam > CUED Speech Group Seminars > Refinements in Hierarchical Phrase-Based Translation

Refinements in Hierarchical Phrase-Based Translation

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Rogier van Dalen.

Hierarchical phrase-based translation is a recent and popular approach for machine translation, especially for language pairs with diverging word order. We first present a more robust way to extract and to estimate hierarchical phrase-based grammars. We show translation improvements on a Chinese-English task. We also present an easy and efficient implementation of hierarchical phrase-based grammar extraction and retrieval using the Hadoop/HBase framework. Finally, we introduce a decoder inspired by a phrase-based translation stack decoder that achieves state-of-the-art performance on the string regeneration task.

A sandwich lunch will be provided.

This talk is part of the CUED Speech Group Seminars series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2017 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity