Paper Info
Title
Language Model Adaptation For A Speech To Sign Language Translation System Using Web Frequencies And A Map Framework
Abstract
This paper presents a successful technique for creating a new language model (LM) that adapts the original target LM used by a machine translation (MT) system. This technique is especially useful for situations where there are very scarce resources for training the target side (Spanish Sign Language (LSE) in our case) in order to properly estimate the target LM, the Sign Language Model (SLM), used by the MT system. The technique uses information from the source language, Spanish in our task, and from the phrase-based translation matrix in order to create a new LM, estimated using web frequencies, which adapts the counts of the SLM through the Maximum A Posteriori method (MAP). The corpus consists of common used sentences spoken by an officer when assisting people in applying for, or renewing, the National Identification Document. The proposed technique allows relative reductions of 15.5% on perplexity and 2.7% on WER for translation, which are close to half the maximum performance obtainable when only the LM is optimized.
Year
Venue
Keywords
2008
INTERSPEECH 2008: 9TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2008, VOLS 1-5
language model adaptation, machine translation, sign language, web counts
Field
DocType
Citations 
Perplexity,Cache language model,Computer science,Machine translation,Phrase,Speech recognition,Sign language,Artificial intelligence,Natural language processing,Constructed language,Maximum a posteriori estimation,Language model
Conference
2
PageRank 
References 
Authors
0.40
12
7
Name
Order
Citations
PageRank
Luis Fernando D'Haro118125.97
Rubén San-Segundo-Hernández217329.60
Ricardo De Córdoba314225.58
Jan Bungeroth4404.45
Daniel Stein522517.59
Hermann Ney6141781506.93
ingenieria electronica720.40