Sciweavers

120 search results - page 5 / 24
» A Word-to-Word Model of Translational Equivalence
Sort
View
CORR
1998
Springer
99views Education» more  CORR 1998»
13 years 7 months ago
Models of Co-occurrence
A model of co-occurrence in bitext is a boolean predicate that indicates whether a given pair of word tokens co-occur in corresponding regions of the bitext space. Co-occurrence i...
I. Dan Melamed
NIPS
2008
13 years 8 months ago
Bayesian Synchronous Grammar Induction
We present a novel method for inducing synchronous context free grammars (SCFGs) from a corpus of parallel string pairs. SCFGs can model equivalence between strings in terms of su...
Phil Blunsom, Trevor Cohn, Miles Osborne
ACL
2008
13 years 8 months ago
Distributed Word Clustering for Large Scale Class-Based Language Modeling in Machine Translation
In statistical language modeling, one technique to reduce the problematic effects of data sparsity is to partition the vocabulary into equivalence classes. In this paper we invest...
Jakob Uszkoreit, Thorsten Brants
ACL
2008
13 years 8 months ago
A Discriminative Latent Variable Model for Statistical Machine Translation
Large-scale discriminative machine translation promises to further the state-of-the-art, but has failed to deliver convincing gains over current heuristic frequency count systems....
Phil Blunsom, Trevor Cohn, Miles Osborne
BIRTHDAY
2003
Springer
14 years 19 days ago
Fair Equivalence Relations
Equivalence between designs is a fundamental notion in verification. The linear and branching approaches to verification induce different notions of equivalence. When the designs...
Orna Kupferman, Nir Piterman, Moshe Y. Vardi