no code implementations • RANLP 2021 • Maja Popović, Alberto Poncelas, Marija Brkic, Andy Way
This work investigates neural machine translation (NMT) systems for translating English user reviews into Croatian and Serbian, two similar morphologically complex languages.
no code implementations • loresmt (COLING) 2022 • Alberto Poncelas, Johanes Effendi
The development of machine translation (MT) has been successful in breaking the language barrier of the world’s top 10-20 languages.
no code implementations • WAT 2022 • Alberto Poncelas, Johanes Effendi, Ohnmar Htun, Sunil Yadav, Dongzhe Wang, Saurabh Jain
This paper introduces our neural machine translation system’s participation in the WAT 2022 shared translation task (team ID: sakura).
no code implementations • WMT (EMNLP) 2020 • Maja Popović, Alberto Poncelas
This paper describes the ADAPT-DCU machine translation systems built for the WMT 2020 shared task on Similar Language Translation.
no code implementations • VarDial (COLING) 2020 • Maja Popović, Alberto Poncelas, Marija Brkic, Andy Way
Furthermore, translation performance from English is much better than from German, partly because German is morphologically more complex and partly because the corpus consists mostly of parallel human translations instead of original text and its human translation.
no code implementations • loresmt (AACL) 2020 • Alberto Poncelas, Jan Buts, James Hadley, Andy Way
As an additional contribution, we made available a set of English-Esperanto parallel data in the literary domain.
no code implementations • AMTA 2020 • Alberto Poncelas, Pintu Lohar, Andy Way, James Hadley
Furthermore, as performing a direct translation is not always possible, we explore the performance of automatic classifiers on sentences that have been translated using a pivot MT system.
no code implementations • ACL 2020 • Xabier Soto, Dimitar Shterionov, Alberto Poncelas, Andy Way
Machine translation (MT) has benefited from using synthetic training data originating from translating monolingual corpora, a technique known as backtranslation.
no code implementations • 1 May 2020 • Andy Way, Rejwanul Haque, Guodong Xie, Federico Gaspari, Maja Popovic, Alberto Poncelas
Every day, more people are becoming infected and dying from exposure to COVID-19.
no code implementations • LREC 2020 • Alberto Poncelas, Wichaya Pidchamook, Chao-Hong Liu, James Hadley, Andy Way
Thai is a low-resource language, so it is often the case that data is not available in sufficient quantities to train an Neural Machine Translation (NMT) model which perform to a high level of quality.
1 code implementation • LREC 2020 • Alberto Poncelas, Mohammad Aboomar, Jan Buts, James Hadley, Andy Way
This paper reports on a tool built for postediting the output of Tesseract, more specifically for correcting common errors in digitized historical documents.
no code implementations • WS 2019 • Alberto Poncelas, Andy Way
Neural Machine Translation (NMT) models tend to achieve best performance when larger sets of parallel sentences are provided for training.
no code implementations • 9 Sep 2019 • Alberto Poncelas, Maja Popovic, Dimitar Shterionov, Gideon Maillette de Buy Wenniger, Andy Way
Neural Machine Translation (NMT) models achieve their best performance when large sets of parallel data are used for training.
no code implementations • RANLP 2019 • Alberto Poncelas, Maja Popovi{\'c}, Dimitar Shterionov, Gideon Maillette de Buy Wenniger, Andy Way
Neural Machine Translation (NMT) models achieve their best performance when large sets of parallel data are used for training.
no code implementations • WS 2019 • Alberto Poncelas, Gideon Maillette de Buy Wenniger, Andy Way
Machine Translation models are trained to translate a variety of documents from one language into another.
no code implementations • 18 Jun 2019 • Alberto Poncelas, Gideon Maillette de Buy Wenniger, Andy Way
These methods ensure that selected sentences share n-grams with the test set so the NMT model can be adapted to translate it.
no code implementations • 23 Feb 2019 • Eva Vanmassenhove, Amit Moryossef, Alberto Poncelas, Andy Way, Dimitar Shterionov
In contradiction with the results described in previous comparable shared tasks, our neural models performed better than our best traditional approaches with our best feature set-up.
no code implementations • IWSLT (EMNLP) 2018 • Alberto Poncelas, Andy Way, Kepa Sarasola
In this paper we present the ADAPT system built for the Basque to English Low Resource MT Evaluation Campaign.
no code implementations • IWSLT (EMNLP) 2018 • Alberto Poncelas, Gideon Maillette de Buy Wenniger, Andy Way
A limitation of these methods to date is that using the source-side test set does not by itself guarantee that sentences are selected with correct translations, or translations that are suitable given the test-set domain.
no code implementations • WS 2018 • Catarina Cruz Silva, Chao-Hong Liu, Alberto Poncelas, Andy Way
Data selection is a process used in selecting a subset of parallel data for the training of machine translation (MT) systems, so that 1) resources for training might be reduced, 2) trained models could perform better than those trained with the whole corpus, and/or 3) trained models are more tailored to specific domains.
no code implementations • 5 Jun 2018 • Chao-Hong Liu, Declan Groves, Akira Hayakawa, Alberto Poncelas, Qun Liu
Understanding and being able to react to customer feedback is the most fundamental task in providing good customer service.
no code implementations • 17 Apr 2018 • Alberto Poncelas, Dimitar Shterionov, Andy Way, Gideon Maillette de Buy Wenniger, Peyman Passban
A prerequisite for training corpus-based machine translation (MT) systems -- either Statistical MT (SMT) or Neural MT (NMT) -- is the availability of high-quality parallel data.
no code implementations • IJCNLP 2017 • Chao-Hong Liu, Yasufumi Moriya, Alberto Poncelas, Declan Groves
This document introduces the IJCNLP 2017 Shared Task on Customer Feedback Analysis.
no code implementations • IJCNLP 2017 • Daria Dzendzik, Alberto Poncelas, Carl Vogel, Qun Liu
We describe the work of a team from the ADAPT Centre in Ireland in addressing automatic answer selection for the Multi-choice Question Answering in Examinations shared task.