Sciweavers

1380 search results - page 198 / 276
» Decomposable Modeling in Natural Language Processing
Sort
View
EMNLP
2009
14 years 7 months ago
The Feature Subspace Method for SMT System Combination
Recently system combination has been shown to be an effective way to improve translation quality over single machine translation systems. In this paper, we present a simple and ef...
Nan Duan, Mu Li, Tong Xiao, Ming Zhou
EMNLP
2009
14 years 7 months ago
Discriminative Corpus Weight Estimation for Machine Translation
Current statistical machine translation (SMT) systems are trained on sentencealigned and word-aligned parallel text collected from various sources. Translation model parameters ar...
Spyros Matsoukas, Antti-Veikko I. Rosti, Bing Zhan...
EMNLP
2010
14 years 7 months ago
Collective Cross-Document Relation Extraction Without Labelled Data
We present a novel approach to relation extraction that integrates information across documents, performs global inference and requires no labelled text. In particular, we tackle ...
Limin Yao, Sebastian Riedel, Andrew McCallum
UML
2005
Springer
15 years 3 months ago
Bridging Grammarware and Modelware
Abstract. In Software Engineering many text-based languages and supporting tools are used, forming the grammarware technical space. Currently model driven engineering is the new em...
Manuel Wimmer, Gerhard Kramler
SIGIR
2008
ACM
14 years 9 months ago
Generating diverse katakana variants based on phonemic mapping
In Japanese, it is quite common for the same word to be written in several different ways. This is especially true for katakana words which are typically used for transliterating ...
Kazuhiro Seki, Hiroyuki Hattori, Kuniaki Uehara