Sciweavers

EMNLP
2007
13 years 9 months ago
Hierarchical System Combination for Machine Translation
Given multiple translations of the same source sentence, how to combine them to produce a translation that is better than any single system output? We propose a hierarchical syste...
Fei Huang, Kishore Papineni
EMNLP
2007
13 years 9 months ago
Japanese Dependency Analysis Using the Ancestor-Descendant Relation
We propose a novel method for Japanese dependency analysis, which is usually reduced to the construction of a dependency tree. In deterministic approaches to this task, dependency...
Akihiro Tamura, Hiroya Takamura, Manabu Okumura
EMNLP
2007
13 years 9 months ago
Learning to Merge Word Senses
It has been widely observed that different NLP applications require different sense granularities in order to best exploit word sense distinctions, and that for many applications ...
Rion Snow, Sushant Prakash, Daniel Jurafsky, Andre...
LREC
2010
206views Education» more  LREC 2010»
13 years 9 months ago
FreeLing 2.1: Five Years of Open-source Language Processing Tools
FreeLing is an open-source multilingual language processing library providing a wide range of language analyzers for several languages. It offers text processing and language anno...
Lluís Padró, Miquel Collado, Samuel ...
EMNLP
2007
13 years 9 months ago
Learning Structured Models for Phone Recognition
We present a maximally streamlined approach to learning HMM-based acoustic models for automatic speech recognition. In our approach, an initial monophone HMM is iteratively refin...
Slav Petrov, Adam Pauls, Dan Klein
EMNLP
2007
13 years 9 months ago
A Topic Model for Word Sense Disambiguation
We develop latent Dirichlet allocation with WORDNET (LDAWN), an unsupervised probabilistic topic model that includes word sense as a hidden variable. We develop a probabilistic po...
Jordan L. Boyd-Graber, David M. Blei, Xiaojin Zhu
EMNLP
2007
13 years 9 months ago
Adapting the RASP System for the CoNLL07 Domain-Adaptation Task
We describe our submission to the domain adaptation track of the CoNLL07 shared task in the open class for systems using external resources. Our main finding was that it was very...
Rebecca Watson, Ted Briscoe
EMNLP
2007
13 years 9 months ago
Improving Query Spelling Correction Using Web Search Results
Traditional research on spelling correction in natural language processing and information retrieval literature mostly relies on pre-defined lexicons to detect spelling errors. Bu...
Qing Chen, Mu Li, Ming Zhou
EMNLP
2007
13 years 9 months ago
Factored Translation Models
We present an extension of phrase-based statistical machine translation models that enables the straight-forward integration of additional annotation at the word-level — may it ...
Philipp Koehn, Hieu Hoang
EMNLP
2007
13 years 9 months ago
Bayesian Document Generative Model with Explicit Multiple Topics
In this paper, we proposed a novel probabilistic generative model to deal with explicit multiple-topic documents: Parametric Dirichlet Mixture Model(PDMM). PDMM is an expansion of...
Issei Sato, Hiroshi Nakagawa