Monte Carlo techniques for phrase-based translation |
| |
Authors: | Abhishek Arun Barry Haddow Philipp Koehn Adam Lopez Chris Dyer Phil Blunsom |
| |
Affiliation: | 1.University of Edinburgh,Edinburgh,UK;2.University of Maryland,College Park,USA;3.Oxford University Computing Laboratory,Oxford,UK |
| |
Abstract: | Recent advances in statistical machine translation have used approximate beam search for NP-complete inference within probabilistic
translation models. We present an alternative approach of sampling from the posterior distribution defined by a translation
model. We define a novel Gibbs sampler for sampling translations given a source sentence and show that it effectively explores
this posterior distribution. In doing so we overcome the limitations of heuristic beam search and obtain theoretically sound
solutions to inference problems such as finding the maximum probability translation and minimum risk training and decoding. |
| |
Keywords: | |
本文献已被 SpringerLink 等数据库收录! |
|