Carnegie Mellon University
file.pdf (179.14 kB)

Using Variable Decoding Weight for Language Model in Statistical Machine Translation

Download (179.14 kB)
journal contribution
posted on 2010-10-01, 00:00 authored by Behrang Mohit, Rebecca Hwa, Alon LavieAlon Lavie

This paper investigates varying the decoder weight of the language model (LM) when translating different parts of a sentence. We determine the condition under which the LM weight should be adapted. We find that a better translation can be achieved by varying the LM weight when decoding the most problematic spot in a sentence, which we refer to as a difficult segment. Two adaptation strategies are proposed and compared through experiments. We find that adapting a different LM weight for every difficult segment resulted in the largest improvement in translation quality


Publisher Statement

Copyright 2010 AMTA



Usage metrics