DE eng

Search in the Catalogues and Directories

Page: 1 2 3 4 5 6 7...33
Hits 41 – 60 of 643

41
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
42
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
43
Q. Can knowledge graphs be used to answer Boolean questions? A. It’s complicated!
In: Dzendzik, Daria, Vogel, Carl orcid:0000-0001-8928-8546 and Foster, Jennifer orcid:0000-0002-7789-4853 (2020) Q. Can knowledge graphs be used to answer Boolean questions? A. It’s complicated! In: First Workshop on Insights from Negative Results in NLP, 10 Nov 2020, Online. (2020)
BASE
Show details
44
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
45
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
46
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)
BASE
Show details
47
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
48
The impact of indirect machine translation on sentiment classification
In: Poncelas, Alberto orcid:0000-0002-5089-1687 , Lohar, Pintu, Way, Andy orcid:0000-0001-5736-5930 and Hadley, James orcid:0000-0003-1950-2679 (2020) The impact of indirect machine translation on sentiment classification. In: 14th biennial conference of the Association for Machine Translation in the Americas, AMTA, 6-10 Oct 2020, Orlando, Fl, USA (Virtual). (In Press) (2020)
BASE
Show details
49
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
50
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
51
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. (In Press) (2020)
BASE
Show details
52
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). (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/25240/
BASE
Hide details
53
Identifying and Modeling Code-Switched Language
BASE
Show details
54
Essays on the use of computational linguistics in marketing
BASE
Show details
55
Theoretical, empirical and computational approaches to agreement with coordination structures ; Les approches théoriques, empiriques et computationnelles pour l’accord avec les structures coordonnées
An, Aixiu. - : HAL CCSD, 2020
In: https://tel.archives-ouvertes.fr/tel-03256559 ; Linguistics. Université de Paris, 2020. English. ⟨NNT : 2020UNIP7115⟩ (2020)
BASE
Show details
56
A Method for Projecting Features from Observed Sets of Phonological Classes
In: LINGUISTIC INQUIRY, vol 51, iss 4 (2020)
BASE
Show details
57
Universals of word order reflect optimization of grammars for efficient communication.
In: Proceedings of the National Academy of Sciences of the United States of America, vol 117, iss 5 (2020)
BASE
Show details
58
The Design of Online Environments (Political Hashtags) and the Quality of Democratic Discourse At-Scale
Rho, Eugenia Ha Rim. - : eScholarship, University of California, 2020
BASE
Show details
59
"Set up son? Scam set, asserts Bob": Semi-Automatic Generation of Bilingual Palindromes
In: https://hal-univ-paris8.archives-ouvertes.fr/hal-02560680 ; 2020 (2020)
BASE
Show details
60
Automatic Processing of Aerodynamic Parameters in Parkinsonian Dysarthria
In: Automatic Assessment of Parkinosnian Speech. Ed. Springer Nature Switzerland AG. Communications in Computer and Information Science (CCIS) Series, Vol 1295. ; https://hal.archives-ouvertes.fr/hal-03115366 ; Automatic Assessment of Parkinosnian Speech. Ed. Springer Nature Switzerland AG. Communications in Computer and Information Science (CCIS) Series, Vol 1295., pp.60-76, 2020, ⟨10.1007/978-3-030-65654-6_4⟩ (2020)
BASE
Show details

Page: 1 2 3 4 5 6 7...33

Catalogues
4
0
0
0
0
0
1
Bibliographies
6
0
2
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
634
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern