-
Ergun Biçici.
ParFDA for Instance Selection for Statistical Machine Translation.
In Proc. of the First Conf. on Machine Translation (WMT16),
Berlin, Germany,
pages 252-258,
8 2016.
[WWW]
[PDF]
Keyword(s): Machine Translation,
Machine Learning,
Language Modeling.
Abstract: |
We build parallel feature decay algorithms (ParFDA) Moses statistical machine translation (SMT) systems for all language pairs in the translation task at the first conference on statistical machine translation~\cite{WMT2016} (WMT16). ParFDA obtains results close to the top constrained phrase-based SMT with an average of $2.52$ BLEU points difference using significantly less computation for building SMT systems than the computation that would be spent using all available corpora. We obtain BLEU bounds based on target coverage and show that ParFDA results can be improved by $12.6$ BLEU points on average. Similar bounds show that top constrained SMT results at WMT16 can be improved by $8$ BLEU points on average while German to English and Romanian to English translations results are already close to the bounds. |
@InProceedings{Bicici:ParFDA:WMT2016,
author = {Ergun Bi\c{c}ici},
title = {{ParFDA} for Instance Selection for Statistical Machine Translation},
booktitle = {Proc. of the {F}irst {C}onf. on {M}achine {T}ranslation ({WMT16})},
month = {8},
year = {2016},
pages = {252--258},
address = {Berlin, Germany},
url = {https://aclanthology.info/papers/W16-2306/w16-2306},
keywords = {Machine Translation, Machine Learning, Language Modeling},
pdf = {http://bicici.github.com/publications/2016/ParFDA_WMT.pdf},
abstract = {We build parallel feature decay algorithms (ParFDA) Moses statistical machine translation (SMT) systems for all language pairs in the translation task at the first conference on statistical machine translation~\cite{WMT2016} (WMT16). ParFDA obtains results close to the top constrained phrase-based SMT with an average of $2.52$ BLEU points difference using significantly less computation for building SMT systems than the computation that would be spent using all available corpora. We obtain BLEU bounds based on target coverage and show that ParFDA results can be improved by $12.6$ BLEU points on average. Similar bounds show that top constrained SMT results at WMT16 can be improved by $8$ BLEU points on average while German to English and Romanian to English translations results are already close to the bounds.},
}
-
Ergun Biçici.
RTM at SemEval-2016 Task 1: Predicting Semantic Similarity with Referential Translation Machines and Related Statistics.
In SemEval-2016: Semantic Evaluation Exercises - Inter. Workshop on Semantic Evaluation,
San Diego, CA, USA,
pages 758-764,
6 2016.
[WWW]
Keyword(s): Machine Translation,
Machine Learning,
Performance Prediction,
Semantic Similarity.
Abstract: |
We use referential translation machines (RTMs) for predicting the semantic similarity of text in both STS Core and Cross-lingual STS. RTMs pioneer a language independent approach to all similarity tasks and remove the need to access any task or domain specific information or resource. RTMs become 14th out of 26 submissions in Cross-lingual STS. We also present rankings of various prediction tasks using the performance of RTM in terms of MRAER, a normalized relative absolute error metric. |
@InProceedings{Bicici:RTM:SEMEVAL2016,
author = {Ergun Bi\c{c}ici},
title = {{RTM} at {SemEval-2016} Task 1: Predicting Semantic Similarity with Referential Translation Machines and Related Statistics},
booktitle = {{SemEval-2016}: Semantic Evaluation Exercises - Inter. Workshop on Semantic Evaluation},
month = {6},
year = {2016},
pages = {758--764},
address = {San Diego, CA, USA},
url = {https://aclanthology.info/papers/S16-1117/s16-1117},
abstract = {We use referential translation machines (RTMs) for predicting the semantic similarity of text in both STS Core and Cross-lingual STS. RTMs pioneer a language independent approach to all similarity tasks and remove the need to access any task or domain specific information or resource. RTMs become 14th out of 26 submissions in Cross-lingual STS. We also present rankings of various prediction tasks using the performance of RTM in terms of MRAER, a normalized relative absolute error metric.},
keywords = "Machine Translation, Machine Learning, Performance Prediction, Semantic Similarity",
}
-
Ergun Biçici.
Referential Translation Machines for Predicting Translation Performance.
In Proc. of the First Conf. on Machine Translation (WMT16),
Berlin, Germany,
pages 777-781,
8 2016.
[WWW]
Keyword(s): Machine Translation,
Machine Learning,
Performance Prediction.
Abstract: |
Referential translation machines (RTMs) pioneer a language independent approach for predicting translation performance and to all similarity tasks with top performance in both bilingual and monolingual settings and remove the need to access any task or domain specific information or resource. RTMs achieve to become $1$st in document-level, $4$th system at sentence-level according to mean absolute error, and $4$th in phrase-level prediction of translation quality in quality estimation task. |
@InProceedings{Bicici:RTM:WMT2016,
author = {Ergun Bi\c{c}ici},
title = {Referential Translation Machines for Predicting Translation Performance},
booktitle = {Proc. of the {F}irst {C}onf. on {M}achine {T}ranslation ({WMT16})},
month = {8},
year = {2016},
pages = {777--781},
address = {Berlin, Germany},
url = {https://aclanthology.info/papers/W16-2382/w16-2382},
keywords = "Machine Translation, Machine Learning, Performance Prediction",
abstract = {Referential translation machines (RTMs) pioneer a language independent approach for predicting translation performance and to all similarity tasks with top performance in both bilingual and monolingual settings and remove the need to access any task or domain specific information or resource. RTMs achieve to become $1$st in document-level, $4$th system at sentence-level according to mean absolute error, and $4$th in phrase-level prediction of translation quality in quality estimation task.},
}