| Publications of year 2011 |
| Books and proceedings |
@book{RegMTBook,
author = {Ergun Bi\c{c}ici},
title = {The Regression Model of Machine Translation: Learning, Instance Selection, Decoding, and Evaluation},
year = {2011},
isbn = {3846507490},
pages = {1--172},
publisher = {LAP LAMBERT Academic Publishing},
url = {http://www.amazon.com/Regression-Model-Machine-Translation-Evaluation/dp/3846507490},
}
| Thesis |
| Machine translation is the task of automatically finding the translation of a source sentence in the target language. Statistical machine translation (SMT) use parallel corpora or bilingual paired corpora that are known to be translations of each other to find a likely translation for a given source sentence based on the observed translations. The task of machine translation can be seen as an instance of estimating the functions that map strings to strings. Regression based machine translation (RegMT) approach provides a learning framework for machine translation, separating learning models for training, training instance selection, feature representation, and decoding. We use the transductive learning framework for making the RegMT approach computationally more scalable and consider the model building step independently for each test sentence. We develop training instance selection algorithms that not only make RegMT computationally more scalable but also improve the performance of standard SMT systems. We develop better training instance selection techniques than previous work from given parallel training sentences for achieving more accurate RegMT models using less training instances. We introduce L1 regularized regression as a better model than L2 regularized regression for statistical machine translation. Our results demonstrate that sparse regression models are better than L2 regularized regression for statistical machine translation in predicting target features, estimating word alignments, creating phrase tables, and generating translation outputs. We develop good evaluation techniques for measuring the performance of the RegMT model and the quality of the translations. We use F1 measure, which performs good when evaluating translations into English according to human judgments. F1 allows us to evaluate the performance of the RegMT models using the target feature prediction vectors or the coefficients matrices learned or a given SMT model using its phrase table without performing the decoding step, which can be computationally expensive. Decoding is dependent on the representation of the training set and the features used. We use graph decoding on the prediction vectors represented in $n$-gram or word sequence counts space found in the training set. We also decode using Moses after transforming the learned weight matrix representing the mappings between the source and target features to a phrase table that can be used by Moses during decoding. We demonstrate that sparse L1 regularized regression performs better than L2 regularized regression in the German-English translation task and in the Spanish-English translation task when using small sized training sets. Graph based decoding can provide an alternative to phrase-based decoding in translation domains having low vocabulary. |
@phdthesis{BiciciThesis,
author = {Ergun Bi\c{c}ici},
note = {Supervisor: Deniz Yuret},
title = {The Regression Model of Machine Translation},
year = {2011},
school = {Koç University},
keywords = {Machine Translation, Machine Learning, Artificial Intelligence, Natural Language Processing},
pdf = {http://bicici.github.io/publications/2011/RegMTThesis_Web.pdf},
abstract = {Machine translation is the task of automatically finding the translation of a source sentence in the target language. Statistical machine translation (SMT) use parallel corpora or bilingual paired corpora that are known to be translations of each other to find a likely translation for a given source sentence based on the observed translations. The task of machine translation can be seen as an instance of estimating the functions that map strings to strings.
Regression based machine translation (RegMT) approach provides a learning framework for machine translation, separating learning models for training, training instance selection, feature representation, and decoding. We use the transductive learning framework for making the RegMT approach computationally more scalable and consider the model building step independently for each test sentence. We develop training instance selection algorithms that not only make RegMT computationally more scalable but also improve the performance of standard SMT systems. We develop better training instance selection techniques than previous work from given parallel training sentences for achieving more accurate RegMT models using less training instances.
We introduce L1 regularized regression as a better model than L2 regularized regression for statistical machine translation. Our results demonstrate that sparse regression models are better than L2 regularized regression for statistical machine translation in predicting target features, estimating word alignments, creating phrase tables, and generating translation outputs. We develop good evaluation techniques for measuring the performance of the RegMT model and the quality of the translations. We use F1 measure, which performs good when evaluating translations into English according to human judgments. F1 allows us to evaluate the performance of the RegMT models using the target feature prediction vectors or the coefficients matrices learned or a given SMT model using its phrase table without performing the decoding step, which can be computationally expensive.
Decoding is dependent on the representation of the training set and the features used. We use graph decoding on the prediction vectors represented in $n$-gram or word sequence counts space found in the training set. We also decode using Moses after transforming the learned weight matrix representing the mappings between the source and target features to a phrase table that can be used by Moses during decoding. We demonstrate that sparse L1 regularized regression performs better than L2 regularized regression in the German-English translation task and in the Spanish-English translation task when using small sized training sets. Graph based decoding can provide an alternative to phrase-based decoding in translation domains having low vocabulary.},
}
| Conference articles |
| We present an empirical study of instance selection techniques for machine translation. In an active learning setting, instance selection minimizes the human effort by identifying the most informative sentences for translation. In a transductive learning setting, selection of training instances relevant to the test set improves the final translation quality. After reviewing the state of the art in the field, we generalize the main ideas in a class of instance selection algorithms that use feature decay. Feature decay algorithms increase diversity of the training set by devaluing features that are already included. We show that the feature decay rate has a very strong effect on the final translation quality whereas the initial feature values, inclusion of higher order features, or sentence length normalizations do not. We evaluate the best instance selection methods using a standard Moses baseline using the whole 1.6 million sentence English-German section of the Europarl corpus. We show that selecting the best 3000 training sentences for a specific test sentence is sufficient to obtain a score within 1 BLEU of the baseline, using 5\% of the training data is sufficient to exceed the baseline, and a ~2 BLEU improvement over the baseline is possible by optimally selected subset of the training data. In out-of-domain translation, we are able to reduce the training set size to about 7\% and achieve a similar performance with the baseline. |
@InProceedings{BiciciYuret:ISforMT:WMT11,
author = {Biçici, Ergun and Yuret, Deniz},
title = {Instance Selection for Machine Translation using Feature Decay Algorithms},
booktitle = {{S}ixth {W}orkshop on {S}tatistical {M}achine {T}ranslation},
month = {7},
year = {2011},
address = {Edinburgh, Scotland},
pages = {272--283},
url = {http://www.aclweb.org/anthology/W11-2131},
keywords = {Machine Translation, Machine Learning},
pdf = {bicici.github.io/publications/2011/ISforMTFDA.pdf},
abstract = {We present an empirical study of instance selection techniques for machine translation. In an active learning setting, instance selection minimizes the human effort by identifying the most informative sentences for translation. In a transductive learning setting, selection of training instances relevant to the test set improves the final translation quality. After reviewing the state of the art in the field, we generalize the main ideas in a class of instance selection algorithms that use feature decay. Feature decay algorithms increase diversity of the training set by devaluing features that are already included. We show that the feature decay rate has a very strong effect on the final translation quality whereas the initial feature values, inclusion of higher order features, or sentence length normalizations do not. We evaluate the best instance selection methods using a standard Moses baseline using the whole 1.6 million sentence English-German section of the Europarl corpus. We show that selecting the best 3000 training sentences for a specific test sentence is sufficient to obtain a score within 1 BLEU of the baseline, using 5\% of the training data is sufficient to exceed the baseline, and a ~2 BLEU improvement over the baseline is possible by optimally selected subset of the training data. In out-of-domain translation, we are able to reduce the training set size to about 7\% and achieve a similar performance with the baseline.},
}
| We present the results we obtain using our RegMT system, which uses transductive regression techniques to learn mappings between source and target features of given parallel corpora and use these mappings to generate machine translation outputs. We present results with our instance selection methods that perform feature decay for proper selection of training instances, which plays an important role to learn correct feature mappings. RegMT uses L2 regularized regression as well as L1 regularized regression for sparse regression estimation of target features.We present translation results using our training instance selection methods, translation results using graph decoding, system combination results with RegMT, and performance evaluation with F1 measure over target features. |
@InProceedings{BiciciYuret:RegMT:WMT11,
author = {Biçici, Ergun and Yuret, Deniz},
title = {{RegMT} System for Machine Translation, System Combination, and Evaluation},
booktitle = {{S}ixth {W}orkshop on {S}tatistical {M}achine {T}ranslation},
month = {7},
year = {2011},
address = {Edinburgh, Scotland},
pages = {323--329},
url = {http://www.aclweb.org/anthology/W11-2137},
keywords = {Machine Translation, Machine Learning},
pdf = {bicici.github.io/publications/2011/RegMTSystem.pdf},
abstract = {We present the results we obtain using our RegMT system, which uses transductive regression techniques to learn mappings between source and target features of given parallel corpora and use these mappings to generate machine translation outputs. We present results with our instance selection methods that perform feature decay for proper selection of training instances, which plays an important role to learn correct feature mappings. RegMT uses L2 regularized regression as well as L1 regularized regression for sparse regression estimation of target features.We present translation results using our training instance selection methods, translation results using graph decoding, system combination results with RegMT, and performance evaluation with F1 measure over target features.},
}
This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All person copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.
Les documents contenus dans ces répertoires sont rendus disponibles par les auteurs qui y ont contribué en vue d'assurer la diffusion à temps de travaux savants et techniques sur une base non-commerciale. Les droits de copie et autres droits sont gardés par les auteurs et par les détenteurs du copyright, en dépit du fait qu'ils présentent ici leurs travaux sous forme électronique. Les personnes copiant ces informations doivent adhérer aux termes et contraintes couverts par le copyright de chaque auteur. Ces travaux ne peuvent pas être rendus disponibles ailleurs sans la permission explicite du détenteur du copyright.
This document was translated from BibTEX by bibtex2html