2 |
Modelling source- and target-language syntactic Information as conditional context in interactive neural machine translation
|
|
|
|
In: Gupta, Kamal Kumar, Haque, Rejwanul orcid:0000-0003-1680-0099 , Ekbal, Asif, Bhattacharyya, Pushpak and Way, Andy orcid:0000-0001-5736-5930 (2020) Modelling source- and target-language syntactic Information as conditional context in interactive neural machine translation. In: Proceedings of the 22nd Annual Conference of the European Association for Machine Translation, 2-6 Nov 2020, Lisboa, Portugal. (2020)
|
|
BASE
|
|
Show details
|
|
3 |
Syntax-informed interactive neural machine translation
|
|
|
|
In: Gupta, Kamal Kumar, Haque, Rejwanul orcid:0000-0003-1680-0099 , Ekbal, Asif, Bhattacharyya, Pushpak and Way, Andy orcid:0000-0001-5736-5930 (2020) Syntax-informed interactive neural machine translation. In: The International Joint Conference on Neural Networks (IJCNN), 19-24 July 2020, Glasgow, UK (Online). (2020)
|
|
BASE
|
|
Show details
|
|
4 |
Rapid development of competitive translation engines for access to multilingual COVID-19 information
|
|
|
|
In: Way, Andy orcid:0000-0001-5736-5930 , Haque, Rejwanul orcid:0000-0003-1680-0099 , Xie, Guodong, Gaspari, Federico orcid:0000-0003-3808-8418 , Popović, Maja orcid:0000-0001-8234-8745 and Poncelas, Alberto orcid:0000-0002-5089-1687 (2020) Rapid development of competitive translation engines for access to multilingual COVID-19 information. Informatics . ISSN 2227-9709 (2020)
|
|
BASE
|
|
Show details
|
|
5 |
The ADAPT’s submissions to the WMT20 biomedical translation task
|
|
|
|
In: Nayak, Prashanth, Haque, Rejwanul orcid:0000-0003-1680-0099 and Way, Andy orcid:0000-0001-5736-5930 (2020) The ADAPT’s submissions to the WMT20 biomedical translation task. In: The Fifrth Conference on Machine Translation (The Biomedical Shared Task), 19-20 Nov 2020, Dominican Republic (Online). (In Press) (2020)
|
|
BASE
|
|
Show details
|
|
6 |
Terminology-aware sentence mining for NMT domain adaptation: ADAPT’s submission to the Adap-MT 2020 English-to-Hindi AI translation shared task
|
|
|
|
In: Haque, Rejwanul orcid:0000-0003-1680-0099 , Moslem, Yasmin orcid:0000-0003-4595-6877 and Way, Andy orcid:0000-0001-5736-5930 (2020) Terminology-aware sentence mining for NMT domain adaptation: ADAPT’s submission to the Adap-MT 2020 English-to-Hindi AI translation shared task. In: Workshop on Low Resource Domain Adaptation for Indic Machine Translation (Adap-MT 2020), 18-21 Dec 2020, Patna, India (Online). (2020)
|
|
BASE
|
|
Show details
|
|
7 |
Investigating query expansion and coreference resolution in question answering on BERT
|
|
|
|
In: Bhattacharjee, Santanu, Haque, Rejwanul orcid:0000-0003-1680-0099 , Maillette de Buy Wenniger, Gideon and Way, Andy orcid:0000-0001-5736-5930 (2020) Investigating query expansion and coreference resolution in question answering on BERT. In: 25th International Conference on Natural Language & Information Systems (NLDB 2020)), 24 - 26 June 2020, Saarbrücken, Germany (Online). ISBN 978-3-030-51309-2 (2020)
|
|
BASE
|
|
Show details
|
|
8 |
Identifying complaints from product reviews: a case study on Hindi
|
|
|
|
In: Singh, Raghvendra Pratap, Haque, Rejwanul orcid:0000-0003-1680-0099 , Hasanuzzaman, Mohammed orcid:0000-0003-1838-0091 and Way, Andy orcid:0000-0001-5736-5930 (2020) Identifying complaints from product reviews: a case study on Hindi. In: 28th Irish Conference on Artificial Intelligence and Cognitive Science, 7-8 Dec 2020, Dublin, Ireland. (2020)
|
|
BASE
|
|
Show details
|
|
9 |
The ADAPT Centre’s neural MT systems for the WAT 2020 document-level translation task
|
|
|
|
In: Jooste, Wandri, Haque, Rejwanul orcid:0000-0003-1680-0099 and Way, Andy orcid:0000-0001-5736-5930 (2020) The ADAPT Centre’s neural MT systems for the WAT 2020 document-level translation task. In: 7th Workshop on Asian Translation (WAT2020), 4 Dec 2020, Suzhou, China (Online). (2020)
|
|
BASE
|
|
Show details
|
|
10 |
Investigating low-resource machine translation for English-to-Tamil
|
|
|
|
In: Ramesh, Akshai, Parthasarathy, Venkatesh Balavadhani, Haque, Rejwanul orcid:0000-0003-1680-0099 and Way, Andy orcid:0000-0001-5736-5930 (2020) Investigating low-resource machine translation for English-to-Tamil. In: Proceedings of the 3rd Workshop on Technologies for MT of Low Resource Languages (LoResMT 2020) AACL-IJCNLP, December 4-7, 2020, Suzhou, China (Online). (2020)
|
|
BASE
|
|
Show details
|
|
11 |
The ADAPT system description for the STAPLE 2020 English-to-Portuguese translation task
|
|
|
|
In: Haque, Rejwanul orcid:0000-0003-1680-0099 , Moslem, Yasmin and Way, Andy orcid:0000-0001-5736-5930 (2020) The ADAPT system description for the STAPLE 2020 English-to-Portuguese translation task. In: 4th Workshop on Neural Generation and Translation (WNGT 2020), 10 July 2020, Seattle, WA, USA (Online). (2020)
|
|
BASE
|
|
Show details
|
|
12 |
An error-based investigation of statistical and neural machine translation performance on Hindi-to-Tamil and English-to-Tamil
|
|
|
|
In: Ramesh, Akshai, Parthasarathy, Venkatesh Balavadhani, Haque, Rejwanul orcid:0000-0003-1680-0099 and Way, Andy orcid:0000-0001-5736-5930 (2020) An error-based investigation of statistical and neural machine translation performance on Hindi-to-Tamil and English-to-Tamil. In: 7th Workshop on Asian Translation (WAT2020), 4 Dec 2020, Suzhou, China (Online). (2020)
|
|
BASE
|
|
Show details
|
|
13 |
The ADAPT system description for the WMT20 news translation task
|
|
|
|
In: Parthasarathy, Venkatesh Balavadhani, Ramesh, Akshai, Haque, Rejwanul orcid:0000-0003-1680-0099 and Way, Andy orcid:0000-0001-5736-5930 (2020) The ADAPT system description for the WMT20 news translation task. In: Fifth Conference on Machine Translation (NEWS Shared Task), 19 -20 Nov 2020, Dominican Republic (Online). (2020)
|
|
BASE
|
|
Show details
|
|
14 |
Terminology-aware sentence mining for NMT domain adaptation: ADAPT’s submission to the Adap-MT 2020 English-to-Hindi AI translation shared task
|
|
|
|
In: Haque, Rejwanul orcid:0000-0003-1680-0099 , Moslem, Yasmin orcid:0000-0003-4595-6877 and Way, Andy orcid:0000-0001-5736-5930 (2020) Terminology-aware sentence mining for NMT domain adaptation: ADAPT’s submission to the Adap-MT 2020 English-to-Hindi AI translation shared task. In: Workshop on Low Resource Domain Adaptation for Indic Machine Translation (Adap-MT 2020), 18-21 Dec 2020, Patna, India (Online). (In Press) (2020)
|
|
BASE
|
|
Show details
|
|
15 |
Arabisc: context-sensitive neural spelling checker
|
|
|
|
In: Moslem, Yasmin orcid:0000-0003-4595-6877 , Haque, Rejwanul orcid:0000-0003-1680-0099 and Way, Andy orcid:0000-0001-5736-5930 (2020) Arabisc: context-sensitive neural spelling checker. In: Proceedings of the AACL Workshop of Natural Language Processing Techniques for Educational Application (NLP-TEA), Asia-Pacific Chapter of the Association for Computational Linguistics (AACL), 4 Dec 2020, Suzhou, China (Online). (In Press) (2020)
|
|
BASE
|
|
Show details
|
|
16 |
The ADAPT system description for the STAPLE 2020 English-to-Portuguese translation task
|
|
|
|
In: Haque, Rejwanul orcid:0000-0003-1680-0099 , Moslem, Yasmin orcid:0000-0003-4595-6877 and Way, Andy orcid:0000-0001-5736-5930 (2020) The ADAPT system description for the STAPLE 2020 English-to-Portuguese translation task. In: Fourth Workshop on Neural Generation and Translation (WNGT), Association for Computational Linguistics (ACL), 10 July 2020, Seattle, WA, USA (Online). (2020)
|
|
BASE
|
|
Show details
|
|
17 |
Arabisc: context-sensitive neural spelling checker
|
|
|
|
In: Moslem, Yasmin orcid:0000-0003-4595-6877 , Haque, Rejwanul orcid:0000-0003-1680-0099 and Way, Andy orcid:0000-0001-5736-5930 (2020) Arabisc: context-sensitive neural spelling checker. In: AACL Workshop of Natural Language Processing Techniques for Educational Application (NLP-TEA), Asia-Pacific Chapter of the Association for Computational Linguistics (AACL), 4 Dec 2020, Suzhou, China (Online). (2020)
|
|
Abstract:
Traditional statistical approaches to spelling correction usually consist of two consecutive processes – error detection and correction – and they are generally computationally intensive. Current state-of-the-art neural spelling correction models usually attempt to correct spelling errors directly over an entire sentence, which, as a consequence, lacks control of the process, e.g. they are prone to overcorrection. In recent years, recurrent neural networks (RNNs), in particular long short-term memory (LSTM) hidden units, have proven increasingly popular and powerful models for many natural language processing (NLP) problems. Accordingly, we made use of a bidirectional LSTM language model (LM) for our context-sensitive spelling detection and correction model which is shown to have much control over the correction process. While the use of LMs for spelling checking and correction is not new to this line of NLP research, our proposed approach makes better use of the rich neighbouring context, not only from before the word to be corrected, but also after it, via a dual-input deep LSTM network. Although in theory our proposed approach can be applied to any language, we carried out our experiments on Arabic, which we believe adds additional value given the fact that there are limited linguistic resources readily available in Arabic in comparison to many languages. Our experimental results demonstrate that the pro- posed methods are effective in both improving the quality of correction suggestions and minimising overcorrection.
|
|
Keyword:
Computational linguistics; Computer engineering; Machine learning; Spelling Checking; Spelling Correction
|
|
URL: http://doras.dcu.ie/25403/
|
|
BASE
|
|
Hide details
|
|
18 |
The ADAPT system description for the STAPLE 2020 English-to-Portuguese translation task
|
|
|
|
In: Haque, Rejwanul orcid:0000-0003-1680-0099 , Moslem, Yasmin orcid:0000-0003-4595-6877 and Way, Andy orcid:0000-0001-5736-5930 (2020) The ADAPT system description for the STAPLE 2020 English-to-Portuguese translation task. In: Fourth Workshop on Neural Generation and Translation (WNGT), Association for Computational Linguistics (ACL), 10 July 2020, Seattle, WA, USA (Online). (2020)
|
|
BASE
|
|
Show details
|
|
19 |
Identifying complaints from product reviews in low-resource scenarios via neural machine translation
|
|
|
|
In: Singh, Raghvendra Pratap, Haque, Rejwanul orcid:0000-0003-1680-0099 , Hasanuzzaman, Mohammed orcid:0000-0003-1838-0091 and Way, Andy orcid:0000-0001-5736-5930 (2020) Identifying complaints from product reviews in low-resource scenarios via neural machine translation. In: ICON 2020: 17th International Conference on Natural Language Processing, 18-21 Dec 2020, IIT Patna, India (Online). (2020)
|
|
BASE
|
|
Show details
|
|
20 |
The ADAPT centre’s participation in WAT 2020 English-to-Odia translation task
|
|
|
|
In: Nayak, Prashanth, Haque, Rejwanul orcid:0000-0003-1680-0099 and Way, Andy orcid:0000-0001-5736-5930 (2020) The ADAPT centre’s participation in WAT 2020 English-to-Odia translation task. In: WAT2020 :The 7th Workshop on Asian Translation, 4-7 Dec 2020, Suzhou, China (Online). (2020)
|
|
BASE
|
|
Show details
|
|
|
|