S
Srinivas Bangalore
Researcher at AT&T Labs
Publications - 5
Citations - 159
Srinivas Bangalore is an academic researcher from AT&T Labs. The author has contributed to research in topics: Machine translation & Transfer-based machine translation. The author has an hindex of 5, co-authored 5 publications receiving 158 citations. Previous affiliations of Srinivas Bangalore include AT&T.
Papers
More filters
Proceedings Article
Statistical Machine Translation through Global Lexical Selection and Sentence Reconstruction
TL;DR: This paper presents a novel approach to lexical selection where the target words are associated with the entire source sentence (global) without the need to compute local associations.
Proceedings ArticleDOI
Automatic Acquisition of Hierarchical Transduction Models for Machine Translation
TL;DR: The method has been applied to create an English-Spanish translation model for a Speech translation application, with word accuracy of over 75% as measured by a string-distance comparison to three reference translations.
Patent
Machine Translation Using Global Lexical Selection and Sentence Reconstruction
TL;DR: This article proposed a method for performing translations from a source language to a target language, which comprises receiving a source phrase, generating a target bag of words based on a global lexical selection of words that loosely couples the source words and target words/phrases, and reconstructing a target phrase or sentence by considering all permutations of words with a conditional probability greater than a threshold.
Journal ArticleDOI
Discriminative Machine Translation Using Global Lexical Selection
TL;DR: This article presents models that decouple the steps of lexical selection and lexical reordering with the aim of minimizing the role of word-alignment in machine translation.
Proceedings ArticleDOI
Three models for discriminative machine translation using global lexical selection and sentence reconstruction
TL;DR: This paper presents a novel approach to lexical selection where the target words are associated with the entire source sentence (global) without the need for local associations.