← Back to papers

2008 EMNLP EMNLP 2008

N-gram Weighting: Reducing Training Data Mismatch in Cross-Domain Language Model Estimation

Authors

Bo-June Paul Hsu , James Glass

Related papers

Triplet Lexicon Models for Statistical Machine Translation 2008

Part-of-Speech Tagging for English-Spanish Code-Switched Text 2008

Information Retrieval Oriented Word Segmentation based on Character Association Strength Ranking 2008

HTM: A Topic Model for Hypertexts 2008

Language and Translation Model Adaptation using Comparable Corpora 2008