Sciweavers

EMNLP
2007
13 years 9 months ago
Unsupervised Part-of-Speech Acquisition for Resource-Scarce Languages
This paper proposes a new bootstrapping approach to unsupervised part-of-speech induction. In comparison to previous bootstrapping algorithms developed for this problem, our appro...
Sajib Dasgupta, Vincent Ng
EMNLP
2007
13 years 9 months ago
A Systematic Comparison of Training Criteria for Statistical Machine Translation
We address the problem of training the free parameters of a statistical machine translation system. We show significant improvements over a state-of-the-art minimum error rate tr...
Richard Zens, Sasa Hasan, Hermann Ney
EMNLP
2007
13 years 9 months ago
Improving Statistical Machine Translation Using Word Sense Disambiguation
We show for the first time that incorporating the predictions of a word sense disambiguation system within a typical phrase-based statistical machine translation (SMT) model cons...
Marine Carpuat, Dekai Wu
EMNLP
2007
13 years 9 months ago
Hybrid Ways to Improve Domain Independence in an ML Dependency Parser
This  paper  reports   a   hybridization   experi­ ment, where a baseline ML dependency pars­ er,   LingPars,  was  allowed  access  to Con­ straint Grammar ...
Eckhard Bick
EMNLP
2007
13 years 9 months ago
Improving Translation Quality by Discarding Most of the Phrasetable
It is possible to reduce the bulk of phrasetables for Statistical Machine Translation using a technique based on the significance testing of phrase pair co-occurrence in the para...
Howard Johnson, Joel D. Martin, George F. Foster, ...
EMNLP
2007
13 years 9 months ago
An Empirical Study on Computing Consensus Translations from Multiple Machine Translation Systems
This paper presents an empirical study on how different selections of input translation systems affect translation quality in system combination. We give empirical evidence that t...
Wolfgang Macherey, Franz Josef Och
EMNLP
2007
13 years 9 months ago
Extracting Data Records from Unstructured Biomedical Full Text
In this paper, we address the problem of extracting data records and their attributes from unstructured biomedical full text. There has been little effort reported on this in the ...
Donghui Feng, Gully Burns, Eduard H. Hovy
EMNLP
2007
13 years 9 months ago
Enhancing Single-Document Summarization by Combining RankNet and Third-Party Sources
We present a new approach to automatic summarization based on neural nets, called NetSum. We extract a set of features from each sentence that helps identify its importance in the...
Krysta Marie Svore, Lucy Vanderwende, Christopher ...
EMNLP
2007
13 years 9 months ago
Incremental Generation of Plural Descriptions: Similarity and Partitioning
Approaches to plural reference generation emphasise descriptive brevity, but often lack empirical backing. This paper describes a corpus-based study of plural descriptions, and pr...
Albert Gatt, Kees van Deemter
EMNLP
2007
13 years 9 months ago
Covington Variations
Three versions of the Covington algorithm for non-projective dependency parsing have been tested on the ten different languages for the Multilingual track of the CoNLLX Shared Tas...
Svetoslav Marinov