Sciweavers

164 search results - page 14 / 33
» Improved Word Alignment with Statistics and Linguistic Heuri...
Sort
View
63
Voted
COLING
2010
14 years 4 months ago
Enhancing Morphological Alignment for Translating Highly Inflected Languages
We propose an unsupervised approach utilizing only raw corpora to enhance morphological alignment involving highly inflected languages. Our method focuses on closed-class morpheme...
Minh-Thang Luong, Min-Yen Kan
CICLING
2010
Springer
14 years 4 months ago
A Chunk-Driven Bootstrapping Approach to Extracting Translation Patterns
Abstract. We present a linguistically-motivated sub-sentential alignment system that extends the intersected IBM Model 4 word alignments. The alignment system is chunk-driven and r...
Lieve Macken, Walter Daelemans
75
Voted
ACL
2008
14 years 11 months ago
Enriching Morphologically Poor Languages for Statistical Machine Translation
We address the problem of translating from morphologically poor to morphologically rich languages by adding per-word linguistic information to the source language. We use the synt...
Eleftherios Avramidis, Philipp Koehn
IICAI
2007
14 years 11 months ago
A Java Implementation of an Extended Word Alignment Algorithm Based on the IBM Models
In recent years statistical word alignment models have been widely used for various Natural Language Processing (NLP) problems. In this paper we describe a platform independent and...
G. Chinnappa, Anil Kumar Singh
64
Voted
ACL
2010
14 years 7 months ago
Discriminative Pruning for Discriminative ITG Alignment
While Inversion Transduction Grammar (ITG) has regained more and more attention in recent years, it still suffers from the major obstacle of speed. We propose a discriminative ITG...
Shujie Liu, Chi-Ho Li, Ming Zhou