Ergun Bicici

Also published as: Ergun Biçici


2020

pdf bib
RTM Ensemble Learning Results at Quality Estimation Task
Ergun Biçici
Proceedings of the Fifth Conference on Machine Translation

We obtain new results using referential translation machines (RTMs) with predictions mixed and stacked to obtain a better mixture of experts prediction. We are able to achieve better results than the baseline model in Task 1 subtasks. Our stacking results significantly improve the results on the training sets but decrease the test set results. RTMs can achieve to become the 5th among 13 models in ru-en subtask and 5th in the multilingual track of sentence-level Task 1 based on MAE.

2019

pdf bib
Machine Translation with parfda, Moses, kenlm, nplm, and PRO
Ergun Biçici
Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)

We build parfda Moses statistical machine translation (SMT) models for most language pairs in the news translation task. We experiment with a hybrid approach using neural language models integrated into Moses. We obtain the constrained data statistics on the machine translation task, the coverage of the test sets, and the upper bounds on the translation results. We also contribute a new testsuite for the German-English language pair and a new automated key phrase extraction technique for the evaluation of the testsuite translations.

pdf bib
RTM Stacking Results for Machine Translation Performance Prediction
Ergun Biçici
Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2)

We obtain new results using referential translation machines with increased number of learning models in the set of results that are stacked to obtain a better mixture of experts prediction. We combine features extracted from the word-level predictions with the sentence- or document-level features, which significantly improve the results on the training sets but decrease the test set results.

2018

pdf bib
Robust parfda Statistical Machine Translation Results
Ergun Biçici
Proceedings of the Third Conference on Machine Translation: Shared Task Papers

We build parallel feature decay algorithms (parfda) Moses statistical machine translation (SMT) models for language pairs in the translation task. parfda obtains results close to the top constrained phrase-based SMT with an average of 2.252 BLEU points difference on WMT 2017 datasets using significantly less computation for building SMT systems than that would be spent using all available corpora. We obtain BLEU upper bounds based on target coverage to identify which systems used additional data. We use PRO for tuning to decrease fluctuations in the results and postprocess translation outputs to decrease translation errors due to the casing of words. F1 scores on the key phrases of the English to Turkish testsuite that we prepared reveal that parfda achieves 2nd best results. Truecasing translations before scoring obtained the best results overall.

pdf bib
RTM results for Predicting Translation Performance
Ergun Biçici
Proceedings of the Third Conference on Machine Translation: Shared Task Papers

With improved prediction combination using weights based on their training performance and stacking and multilayer perceptrons to build deeper prediction models, RTMs become the 3rd system in general at the sentence-level prediction of translation scores and achieve the lowest RMSE in English to German NMT QET results. For the document-level task, we compare document-level RTM models with sentence-level RTM models obtained with the concatenation of document sentences and obtain similar results.

2017

pdf bib
RTM at SemEval-2017 Task 1: Referential Translation Machines for Predicting Semantic Similarity
Ergun Biçici
Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017)

We use referential translation machines for predicting the semantic similarity of text in all STS tasks which contain Arabic, English, Spanish, and Turkish this year. RTMs pioneer a language independent approach to semantic similarity and remove the need to access any task or domain specific information or resource. RTMs become 6th out of 52 submissions in Spanish to English STS. We average prediction scores using weights based on the training performance to improve the overall performance.

pdf bib
Predicting Translation Performance with Referential Translation Machines
Ergun Biçici
Proceedings of the Second Conference on Machine Translation

2016

pdf bib
ParFDA for Instance Selection for Statistical Machine Translation
Ergun Biçici
Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers

pdf bib
Referential Translation Machines for Predicting Translation Performance
Ergun Biçici
Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers

pdf bib
RTM at SemEval-2016 Task 1: Predicting Semantic Similarity with Referential Translation Machines and Related Statistics
Ergun Biçici
Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016)

2015

pdf bib
RTM-DCU: Predicting Semantic Similarity with Referential Translation Machines
Ergun Biçici
Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015)

pdf bib
ParFDA for Fast Deployment of Accurate Statistical Machine Translation Systems, Benchmarks, and Statistics
Ergun Biçici | Qun Liu | Andy Way
Proceedings of the Tenth Workshop on Statistical Machine Translation

pdf bib
Referential Translation Machines for Predicting Translation Quality and Related Statistics
Ergun Biçici | Qun Liu | Andy Way
Proceedings of the Tenth Workshop on Statistical Machine Translation

2014

pdf bib
RTM-DCU: Referential Translation Machines for Semantic Similarity
Ergun Biçici | Andy Way
Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014)

pdf bib
Parallel FDA5 for Fast Deployment of Accurate Statistical Machine Translation Systems
Ergun Biçici | Qun Liu | Andy Way
Proceedings of the Ninth Workshop on Statistical Machine Translation

pdf bib
Referential Translation Machines for Predicting Translation Quality
Ergun Biçici | Andy Way
Proceedings of the Ninth Workshop on Statistical Machine Translation

2013

pdf bib
CNGL-CORE: Referential Translation Machines for Measuring Semantic Similarity
Ergun Biçici | Josef van Genabith
Second Joint Conference on Lexical and Computational Semantics (*SEM), Volume 1: Proceedings of the Main Conference and the Shared Task: Semantic Textual Similarity

pdf bib
CNGL: Grading Student Answers by Acts of Translation
Ergun Biçici | Josef van Genabith
Second Joint Conference on Lexical and Computational Semantics (*SEM), Volume 2: Proceedings of the Seventh International Workshop on Semantic Evaluation (SemEval 2013)

pdf bib
Feature Decay Algorithms for Fast Deployment of Accurate Statistical Machine Translation Systems
Ergun Biçici
Proceedings of the Eighth Workshop on Statistical Machine Translation

pdf bib
Referential Translation Machines for Quality Estimation
Ergun Biçici
Proceedings of the Eighth Workshop on Statistical Machine Translation

2011

pdf bib
Instance Selection for Machine Translation using Feature Decay Algorithms
Ergun Biçici | Deniz Yuret
Proceedings of the Sixth Workshop on Statistical Machine Translation

pdf bib
RegMT System for Machine Translation, System Combination, and Evaluation
Ergun Biçici | Deniz Yuret
Proceedings of the Sixth Workshop on Statistical Machine Translation

2010

pdf bib
Adaptive Model Weighting and Transductive Regression for Predicting Best System Combinations
Ergun Biçici | S. Serdar Kozat
Proceedings of the Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR

pdf bib
L1 Regularized Regression for Reranking and System Combination in Machine Translation
Ergun Biçici | Deniz Yuret
Proceedings of the Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR

2009

pdf bib
Modeling Morphologically Rich Languages Using Split Words and Unstructured Dependencies
Deniz Yuret | Ergun Biçici
Proceedings of the ACL-IJCNLP 2009 Conference Short Papers