EMNLP
2008
13 years 9 months ago
2008
This paper describes a lexical trigger model for statistical machine translation. We present various methods using triplets incorporating long-distance dependencies that can go be...
EMNLP
2008
13 years 9 months ago
2008
Minimum Error Rate Training (MERT) is an effective means to estimate the feature function weights of a linear model such that an automated evaluation criterion for measuring syste...
EMNLP
2008
13 years 9 months ago
2008
This paper explores the challenge of scaling up language processing algorithms to increasingly large datasets. While cluster computing has been available in commercial environment...
EMNLP
2008
13 years 9 months ago
2008
We present a novel learning framework for pipeline models aimed at improving the communication between consecutive stages in a pipeline. Our method exploits the confidence scores ...
EMNLP
2008
13 years 9 months ago
2008
EMNLP
2008
13 years 9 months ago
2008
How can the development of ideas in a scientific field be studied over time? We apply unsupervised topic modeling to the ACL Anthology to analyze historical trends in the field of...
EMNLP
2008
13 years 9 months ago
2008
Traditionally, statistical machine translation systems have relied on parallel bi-lingual data to train a translation model. While bi-lingual parallel data are expensive to genera...
EMNLP
2008
13 years 9 months ago
2008
Active learning is well-suited to many problems in natural language processing, where unlabeled data may be abundant but annotation is slow and expensive. This paper aims to shed ...
EMNLP
2008
13 years 9 months ago
2008
We examine the problem of content selection in statistical novel sentence generation. Our approach models the processes performed by professional editors when incorporating materi...
EMNLP
2008
13 years 9 months ago
2008
This paper investigates two strategies for improving coreference resolution: (1) training separate models that specialize in particular types of mentions (e.g., pronouns versus pr...