Carnegie Mellon University
Browse
file.pdf (432.14 kB)

Locally Non-Linear Learning for Statistical Machine Translation via Discretization and Structured Regularization

Download (432.14 kB)
journal contribution
posted on 2014-01-01, 00:00 authored by Jonathan H. Clark, Chris Dyer, Alon LavieAlon Lavie

Linear models, which support efficient learning and inference, are the workhorses of statistical machine translation; however, linear decision rules are less attractive from a modeling perspective. In this work, we introduce a technique for learning arbitrary, rule-local, non-linear feature transforms that improve model expressivity, but do not sacrifice the efficient inference and learning associated with linear models. To demonstrate the value of our technique, we discard the customary log transform of lexical probabilities and drop the phrasal translation probability in favor of raw counts. We observe that our algorithm learns a variation of a log transform that leads to better translation quality compared to the explicit log transform. We conclude that non-linear responses play an important role in SMT, an observation that we hope will inform the efforts of feature engineers.

History

Publisher Statement

Copyright (c) 2014 Association for Computational Linguistics

Date

2014-01-01

Usage metrics

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC