Difference between revisions of "Ravi and Knight, ACL 2011"
| Line 16: | Line 16: | ||
== Description of the Method == | == Description of the Method == | ||
| + | |||
| + | [[Word Alignment]] models using parallel corpora is viewed as a maximization problem with latent word alignments <math>a</math> for a set of sentence pairs <math>(s,t)</math>, given by: | ||
| + | |||
| + | <math> | ||
| + | argmax_\theta \prod_{s,t} P_\theta (s|t) | ||
| + | </math> | ||
== Experimental Results == | == Experimental Results == | ||
== Related Work == | == Related Work == | ||
Revision as of 13:38, 30 October 2011
Contents
Citation
S. Ravi and K. Knight. 2011. Deciphering Foreign Language. In Proceedings of ACL.
Online version
Summary
This work addresses the Machine Translation problem without resorting to parallel training data.
This is done by looking at the Machine Translation task from the decipherment perspective, where a sentence in the source language is viewed as the sentence target, but encoded in some unknown symbols.
Experimental showed that, while the results using monolingual data were considerably lower than those using bilingual data if the same amount of data is used, large amounts of monolingual data can be used to create models that perform similarly to systems that use smaller amounts of bilingual data. This is encouraging, since bilingual data is a scarce resource for most language pairs and domains, while monolingual data is much more abundant.
Description of the Method
Word Alignment models using parallel corpora is viewed as a maximization problem with latent word alignments for a set of sentence pairs , given by:
