3 |
The DCU-EPFL Enhanced Dependency Parser at the IWPT 2021 Shared Task ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
The DCU-EPFL Enhanced Dependency Parser at the IWPT 2021 Shared Task
|
|
|
|
In: http://infoscience.epfl.ch/record/289182 (2021)
|
|
BASE
|
|
Show details
|
|
7 |
Treebank embedding vectors for out-of-domain dependency parsing
|
|
|
|
In: Wagner, Joachim orcid:0000-0002-8290-3849 , Barry, James orcid:0000-0003-3051-585X and Foster, Jennifer orcid:0000-0002-7789-4853 (2020) Treebank embedding vectors for out-of-domain dependency parsing. In: 58th Annual Meeting of the Association for Computational Linguistics (ACL 2020), 05-10 Jul 2020, Online (virtual conference). (2020)
|
|
BASE
|
|
Show details
|
|
8 |
APE through neural and statistical MT with augmented data: ADAPT/DCU submission to the WMT 2019 APE Shared task
|
|
|
|
In: Shterionov, Dimitar orcid:0000-0001-6300-797X , Wagner, Joachim orcid:0000-0002-8290-3849 and do Carmo, Félix orcid:0000-0003-4193-3854 (2019) APE through neural and statistical MT with augmented data: ADAPT/DCU submission to the WMT 2019 APE Shared task. In: Fourth Conference on Machine Translation (WMT19), 01-02 Aug 2019, Florence, Italy. (2019)
|
|
Abstract:
Automatic post-editing (APE) can be reduced to a machine translation (MT) task, where the source is the output of a specific MT system and the target is its post-edited variant. However, this approach does not consider context information that can be found in the original source of the MT system. Thus a better approach is to employ multi-source MT, where two input sequences are considered – the original source and the MT output. Extra context information can be introduced in the form of extra tokens that identify certain global properties of a group of segments, added as a prefix or a suffix to each segment. Successfully applied in domain adaptation of MT as well as on APE, this technique deserves further attention. In this work we investigate multi-source neural APE (or NPE) systems with training data which has been augmented with two types of extra context tokens. We experiment with authentic and synthetic data provided by WMT 2019 and submit our results to the APE shared task. We also experiment with using statistical machine translation (SMT) methods for APE. While our systems score bellow the baseline, we consider this work a step towards understanding the added value of extra context in the case of APE.
|
|
Keyword:
Machine translating
|
|
URL: http://doras.dcu.ie/23917/
|
|
BASE
|
|
Hide details
|
|
9 |
Cross-lingual parsing with polyglot training and multi-treebank learning: a Faroese case study
|
|
|
|
In: Barry, James orcid:0000-0003-3051-585X , Wagner, Joachim orcid:0000-0002-8290-3849 and Foster, Jennifer orcid:0000-0002-7789-4853 (2019) Cross-lingual parsing with polyglot training and multi-treebank learning: a Faroese case study. In: The 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019), 3 - 5 Nov 2019, Hong Kong, China. ISBN 978-1-950737-78-9 (2019)
|
|
BASE
|
|
Show details
|
|
10 |
Automatic processing of code-mixed social media content
|
|
Barman, Utsab. - : Dublin City University. School of Computing, 2019. : Dublin City University. ADAPT, 2019
|
|
In: Barman, Utsab (2019) Automatic processing of code-mixed social media content. PhD thesis, Dublin City University. (2019)
|
|
BASE
|
|
Show details
|
|
11 |
Cross-lingual Parsing with Polyglot Training and Multi-treebank Learning: A Faroese Case Study ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Part-of-speech tagging of code-mixed social media content: pipeline, stacking and joint modelling
|
|
|
|
In: Barman, Utsab, Wagner, Joachim orcid:0000-0002-8290-3849 and Foster, Jennifer orcid:0000-0002-7789-4853 (2016) Part-of-speech tagging of code-mixed social media content: pipeline, stacking and joint modelling. In: Second Workshop on Computational Approaches to Code Switching, 2 Nov 2016, Austin, Texas, USA. (2016)
|
|
BASE
|
|
Show details
|
|
13 |
DCU-ADAPT: Learning edit operations for microblog normalisation with the generalised perceptron
|
|
|
|
In: Wagner, Joachim orcid:0000-0002-8290-3849 and Foster, Jennifer orcid:0000-0002-7789-4853 (2015) DCU-ADAPT: Learning edit operations for microblog normalisation with the generalised perceptron. In: ACL 2015 Workshop on Noisy User-generated Text (W-NUT), 31 July 2015, Beijing, China. (2015)
|
|
BASE
|
|
Show details
|
|
14 |
Code mixing: a challenge for language identification in the language of social media
|
|
|
|
In: Barman, Utsab, Das, Amitava orcid:0000-0003-3418-463X , Wagner, Joachim orcid:0000-0002-8290-3849 and Foster, Jennifer orcid:0000-0002-7789-4853 (2014) Code mixing: a challenge for language identification in the language of social media. In: First Workshop on Computational Approaches to Code Switching, 25 Oct 2014, Doha, Qatar. (2014)
|
|
BASE
|
|
Show details
|
|
15 |
DCU: aspect-based polarity classification for SemEval task 4
|
|
|
|
In: Wagner, Joachim orcid:0000-0002-8290-3849 , Arora, Piyush orcid:0000-0002-4261-2860 , Cortes, Santiago, Barman, Utsab, Bogdanova, Dasha, Foster, Jennifer orcid:0000-0002-7789-4853 and Tounsi, Lamia (2014) DCU: aspect-based polarity classification for SemEval task 4. In: International Workshop on Semantic Evaluation (SemEval-2014), 23-24 Aug 2014, Dublin, Ireland. ISBN 978-1-941643-24-2 (2014)
|
|
BASE
|
|
Show details
|
|
16 |
DCU-Symantec at the WMT 2013 Quality Estimation Shared Task
|
|
|
|
In: Rubino, Raphael, Wagner, Joachim orcid:0000-0002-8290-3849 , Foster, Jennifer orcid:0000-0002-7789-4853 , Roturier, Johann, Samad Zadeh Kaljahi, Rasoul and Hollowood, Fred (2013) DCU-Symantec at the WMT 2013 Quality Estimation Shared Task. In: 8th Workshop on Statistical Machine Translation, 8-9 Aug 2013, Sofia, Bulgaria. ISBN 978-1-937284-57-2 (2013)
|
|
BASE
|
|
Show details
|
|
17 |
DCU-Paris13 systems for the SANCL 2012 shared task
|
|
|
|
In: Le Roux, Joseph, Foster, Jennifer orcid:0000-0002-7789-4853 , Wagner, Joachim orcid:0000-0002-8290-3849 , Samad Zadeh Kaljahi, Rasoul and Bryl, Anton (2012) DCU-Paris13 systems for the SANCL 2012 shared task. In: The NAACL 2012 First Workshop on Syntactic Analysis of Non-Canonical Language (SANCL), 7-8 Jun 2012, Montreal, Quebec, Canada. (2012)
|
|
BASE
|
|
Show details
|
|
18 |
DCU-Symantec submission for the WMT 2012 quality estimation task
|
|
|
|
In: Rubino, Raphael, Foster, Jennifer orcid:0000-0002-7789-4853 , Wagner, Joachim orcid:0000-0002-8290-3849 , Roturier, Johann, Samad Zadeh Kaljahi, Rasoul and Hollowood, Fred (2012) DCU-Symantec submission for the WMT 2012 quality estimation task. In: The NAACL 2012 Seventh Workshop on Statistical Machine Translation (WMT'12), 7-8 Jun 2012, Montreal, Quebec, Canada. (2012)
|
|
BASE
|
|
Show details
|
|
19 |
Detecting grammatical errors with treebank-induced, probabilistic parsers
|
|
|
|
In: Wagner, Joachim orcid:0000-0002-8290-3849 (2012) Detecting grammatical errors with treebank-induced, probabilistic parsers. PhD thesis, Dublin City University. (2012)
|
|
BASE
|
|
Show details
|
|
20 |
Comparing the use of edited and unedited text in parser self-training
|
|
|
|
In: Foster, Jennifer orcid:0000-0002-7789-4853 , Cetinoglu, Ozlem, Wagner, Joachim orcid:0000-0002-8290-3849 and van Genabith, Josef orcid:0000-0003-1322-7944 (2011) Comparing the use of edited and unedited text in parser self-training. In: The 12th International Conference on Parsing Technologies (IWPT 2011), 05-07 Oct 2011, Dublin, Ireland. ISBN 978-1-932432-04-6 (2011)
|
|
BASE
|
|
Show details
|
|
|
|