Results 1 - 7 of 7

Model combination for machine translation

by John Denero, Shankar Kumar, Ciprian Chelba, Franz Och - IN PROCEEDINGS NAACL-HLT , 2010
"... Machine translation benefits from two types of decoding techniques: consensus decoding over multiple hypotheses under a single model and system combination over hypotheses from different models. We present model combination, a method that integrates consensus decoding and system combination into a u ..."
Abstract - Cited by 18 (0 self) - Add to MetaCart
Machine translation benefits from two types of decoding techniques: consensus decoding over multiple hypotheses under a single model and system combination over hypotheses from different models. We present model combination, a method that integrates consensus decoding and system combination into a unified, forest-based technique. Our approach makes few assumptions about the underlying component models, enabling us to combine systems with heterogenous structure. Unlike most system combination techniques, we reuse the search space of component models, which entirely avoids the need to align translation hypotheses. Despite its relative simplicity, model combination improves translation quality over a pipelined approach of first applying consensus decoding to individual systems, and then applying system combination to their output. We demonstrate BLEU improvements across data sets and language pairs in large-scale experiments.

Joint optimization for machine translation system combination

by Xiaodong He, Kristina Toutanova - in Proc. EMNLP , 2009
"... System combination has emerged as a powerful method for machine translation (MT). This paper pursues a joint optimization strategy for combining outputs from multiple MT systems, where word alignment, ordering, and lexical selection decisions are made jointly according to a set of feature functions ..."
Abstract - Cited by 11 (2 self) - Add to MetaCart
System combination has emerged as a powerful method for machine translation (MT). This paper pursues a joint optimization strategy for combining outputs from multiple MT systems, where word alignment, ordering, and lexical selection decisions are made jointly according to a set of feature functions combined in a single log-linear model. The decoding algorithm is described in detail and a set of new features that support this joint decoding approach is proposed. The approach is evaluated in comparison to state-of-the-art confusion-network-based system combination methods using equivalent features and shown to outperform them significantly. 1

Positive diversity tuning for machine translation system combination

by Daniel Cer , Christopher D Manning , Daniel Jurafsky - In Proceedings of the Eighth Workshop on Statistical Machine Translation , 2013
"... Abstract We present Positive Diversity Tuning, a new method for tuning machine translation models specifically for improved performance during system combination. System combination gains are often limited by the fact that the translations produced by the different component systems are too similar ..."
Abstract - Cited by 4 (0 self) - Add to MetaCart
Abstract We present Positive Diversity Tuning, a new method for tuning machine translation models specifically for improved performance during system combination. System combination gains are often limited by the fact that the translations produced by the different component systems are too similar to each other. We propose a method for reducing excess cross-system similarity by optimizing a joint objective that simultaneously rewards models for producing translations that are similar to reference translations, while also punishing them for translations that are too similar to those produced by other systems. The formulation of the Positive Diversity objective is easy to implement and allows for its quick integration with most machine translation tuning pipelines. We find that individual systems tuned on the same data to Positive Diversity can be even more diverse than systems built using different data sets, while still obtaining good BLEU scores. When these individual systems are used together for system combination, our approach allows for significant gains of 0.8 BLEU even when the combination is performed using a small number of otherwise identical individual systems.
(Show Context)

Voting on N-grams for Machine Translation System Combination

by Kenneth Heafield, Alon Lavie
"... System combination exploits differences between machine translation systems to form a combined translation from several system outputs. Core to this process are features that reward n-gram matches between a candidate combination and each system output. Systems differ in performance at the n-gram lev ..."
Abstract - Cited by 4 (1 self) - Add to MetaCart
System combination exploits differences between machine translation systems to form a combined translation from several system outputs. Core to this process are features that reward n-gram matches between a candidate combination and each system output. Systems differ in performance at the n-gram level despite similar overall scores. We therefore advocate a new feature formulation: for each system and each small n, a feature counts n-gram matches between the system and candidate. We show post-evaluation improvement of 6.67 BLEU over the best system on NIST MT09 Arabic-English test data. Compared to a baseline system combination scheme from WMT 2009, we show improvement in the range of 1 BLEU point. 1
(Show Context)

ABSTRACT Ensemble Methods for Historical Machine-Printed Document Recognition

by William B. Lund, William B. Lund, Michael Jones, Mark Clement, William B. Lund , 2014
"... This Dissertation is brought to you for free and open access by BYU ScholarsArchive. It has been accepted for inclusion in All Theses and Dissertations by an authorized administrator of BYU ScholarsArchive. For more information, please contact scholarsarchive@byu.edu. ..."
Abstract - Add to MetaCart
This Dissertation is brought to you for free and open access by BYU ScholarsArchive. It has been accepted for inclusion in All Theses and Dissertations by an authorized administrator of BYU ScholarsArchive. For more information, please contact scholarsarchive@byu.edu.
(Show Context)

Bi-Gram based Probabilistic Language Model for Template Messaging

by Rina Damdoo
"... This work reports the benefits of Statistical Machine Translation (SMT) in template messaging domain. SMT has become an actual and practical technology due to significant increment in both the computational power and storage capacity of computers and the availability of large volumes of bilingual da ..."
Abstract - Add to MetaCart
This work reports the benefits of Statistical Machine Translation (SMT) in template messaging domain. SMT has become an actual and practical technology due to significant increment in both the computational power and storage capacity of computers and the availability of large volumes of bilingual data. Through SMT a sentences written with misspelled words, short forms and chatting slang can be corrected. The problem of machine translation is to automatically produce a target-language (e.g., Long form English) sentence from a given source-language (e.g., Short form message) sentence. SMS Lingo is a language used by youngsters for instant messaging or for chatting on social networking websites called chatting slang. Such terms often originate with the purpose of saving keystrokes.

Hybrid System Combination for Machine Translation: An Integration of Phrase-level and Sentence-level Combination Approaches

by Wei-yun Ma , 2014
"... Given the wide range of successful statistical MT approaches that have emerged recently, it would be beneficial to take advantage of their individual strengths and avoid their individual weaknesses. Multi-Engine Machine Translation (MEMT) attempts to do so by either fusing the output of multiple tra ..."
Abstract - Add to MetaCart
Given the wide range of successful statistical MT approaches that have emerged recently, it would be beneficial to take advantage of their individual strengths and avoid their individual weaknesses. Multi-Engine Machine Translation (MEMT) attempts to do so by either fusing the output of multiple translation engines or selecting the best translation among them, aiming to improve the overall translation quality. In this thesis, we propose to use the phrase or the sentence as our combination unit instead of the word; three new phrase-level models and one sentence-level model with novel features are proposed. This contrasts with the most popular system combination technique to date which relies on word-level confusion network decoding. Among the three new phrase-level models, the first one utilizes source sentences and target translation hypotheses to learn hierarchical phrases — phrases that contain subphrases (Chiang 2007). It then re-decodes the source sentences using the hierarchical phrases to combine the results of multiple MT systems. The other two models we propose view combination as a paraphrasing process and use paraphrasing rules. The paraphrasing rules are composed of either string-to-string paraphrases or hierarchical paraphrases, learned from monolingual word alignments between a selected best translation hypothesis and other hypotheses. Our