21 |
Transductive data-selection algorithms for fine-tuning neural machine translation
|
|
|
|
In: Poncelas, Alberto orcid:0000-0002-5089-1687 , Maillette de Buy Wenniger, Gideon orcid:0000-0001-8427-7055 and Way, Andy orcid:0000-0001-5736-5930 (2019) Transductive data-selection algorithms for fine-tuning neural machine translation. In: The 8th Workshop on Patent and Scientific Literature Translation, Dublin, Ireland. (2019)
|
|
BASE
|
|
Show details
|
|
22 |
Investigating backtranslation for the improvement of English-Irish machine translation
|
|
|
|
In: Dowling, Meghan orcid:0000-0003-1637-4923 , Lynn, Teresa and Way, Andy orcid:0000-0001-5736-5930 (2019) Investigating backtranslation for the improvement of English-Irish machine translation. Teanga, 26 . pp. 1-25. ISSN 0332-205X (2019)
|
|
BASE
|
|
Show details
|
|
23 |
Predicting students' academic performance and main behavioral features using data mining techniques
|
|
|
|
In: Almutairi, Suad, Shaiba, Hadil and Bezbradica, Marija orcid:0000-0001-9366-5113 (2019) Predicting students' academic performance and main behavioral features using data mining techniques. In: Advances in Data Science, Cyber Security and IT Applications. ICC 2019., 10-12 Dec 2019, Riyadh, Saudi Arabia. ISBN 978-3-030-36364-2 (2019)
|
|
BASE
|
|
Show details
|
|
24 |
Discourse-aware neural machine translation
|
|
Longyue, Wang. - : Dublin City University. School of Computing, 2019. : Dublin City University. ADAPT, 2019
|
|
In: Longyue, Wang orcid:0000-0002-9062-6183 (2019) Discourse-aware neural machine translation. PhD thesis, Dublin City University. (2019)
|
|
Abstract:
Machine translation (MT) models usually translate a text by considering isolated sentences based on a strict assumption that the sentences in a text are independent of one another. However, it is a truism that texts have properties of connectedness that go beyond those of their individual sentences. Disregarding dependencies across sentences will harm translation quality especially in terms of coherence, cohesion, and consistency. Previously, some discourse-aware approaches have been investigated for conventional statistical machine translation (SMT). However, this is a serious obstacle for the state-of-the-art neural machine translation (NMT), which recently has surpassed the performance of SMT. In this thesis, we try to incorporate useful discourse information for enhancing NMT models. More specifically, we conduct research on two main parts: 1) exploiting novel document-level NMT architecture; and 2) dealing with a specific discourse phenomenon for translation models. Firstly, we investigate the influence of historical contextual information on the perfor- mance of NMT models. A cross-sentence context-aware NMT model is proposed to consider the influence of previous sentences in the same document. Specifically, this history is summarized using an additional hierarchical encoder. The historical representations are then integrated into the standard NMT model in different strategies. Experimental results on a Chinese–English document-level translation task show that the approach significantly improves upon a strong attention-based NMT system by up to +2.1 BLEU points. In addition, analysis and comparison also give insightful discussions and conclusions for this research direction. Secondly, we explore the impact of discourse phenomena on the performance of MT. In this thesis, we focus on the phenomenon of pronoun-dropping (pro-drop), where, in pro-drop languages, pronouns can be omitted when it is possible to infer the referent from the context. As the data for training a dropped pronoun (DP) generator is scarce, we propose to automatically annotate DPs using alignment information from a large parallel corpus. We then introduce a hybrid approach: building a neural-based DP generator and integrating it into the SMT model. Experimental results on both Chinese–English and Japanese–English translation tasks demonstrate that our approach achieves a significant improvement of up to +1.58 BLEU points with 66% F-score for DP generation accuracy. Motivated by this promising result, we further exploit the DP translation approach for advanced NMT models. A novel reconstruction-based model is proposed to reconstruct the DP-annotated source sentence from the hidden states of either encoder or decoder, or both components. Experimental results on the same translation tasks show that the proposed approach significantly and consistently improves translation performance over a strong NMT baseline, which is trained on DP-annotated parallel data. To avoid the errors propagated from an external DP prediction model, we finally investigate an end-to-end DP translation model. Specifically, we improve the reconstruction-based model from three perspectives. We first employ a shared reconstructor to better exploit encoder and decoder representations. Secondly, we propose to jointly learn to translate and predict DPs. In order to capture discourse information for DP prediction, we finally combine the hierarchical encoder with the DP translation model. Experimental results on the same translation tasks show that our approach significantly improves both translation performance and DP prediction accuracy.
|
|
Keyword:
Computational linguistics; Linguistics; Machine translating
|
|
URL: http://doras.dcu.ie/22903/
|
|
BASE
|
|
Hide details
|
|
25 |
What is the impact of raw MT on Japanese users of Word preliminary results of a usability study using eye-tracking
|
|
|
|
In: Guerberof Arenas, Ana orcid:0000-0001-9820-7074 , Moorkens, Joss orcid:0000-0003-4864-5986 and O'Brien, Sharon orcid:0000-0003-4864-5986 (2019) What is the impact of raw MT on Japanese users of Word preliminary results of a usability study using eye-tracking. In: XVII Machine Translation Summit, 19-23 Aug 2019, Dublin, Ireland. (In Press) (2019)
|
|
BASE
|
|
Show details
|
|
27 |
Learning to Parse Grounded Language using Reservoir Computing
|
|
|
|
In: ICDL-Epirob 2019 - Joint IEEE 9th International Conference on Development and Learning and Epigenetic Robotics ; https://hal.inria.fr/hal-02422157 ; ICDL-Epirob 2019 - Joint IEEE 9th International Conference on Development and Learning and Epigenetic Robotics, Aug 2019, Olso, Norway. ⟨10.1109/devlrn.2019.8850718⟩ ; https://ieeexplore.ieee.org/abstract/document/8850718 (2019)
|
|
BASE
|
|
Show details
|
|
28 |
Phonetic lessons from automatic phonemic transcription: preliminary reflections on Na (Sino-Tibetan) and Tsuut’ina (Dene) data
|
|
|
|
In: ICPhS XIX (19th International Congress of Phonetic Sciences) ; https://halshs.archives-ouvertes.fr/halshs-02059313 ; ICPhS XIX (19th International Congress of Phonetic Sciences), Aug 2019, Melbourne, Australia ; https://icphs2019.org/icphs2019-fullpapers/ (2019)
|
|
BASE
|
|
Show details
|
|
29 |
A Quantitative Framework for Specifying Underlying Representations in Child Language Acquisition
|
|
|
|
BASE
|
|
Show details
|
|
30 |
Willkommenskultur: A Computational and Socio-linguistic Study of Modern German Discourse on Migrant Populations
|
|
|
|
In: Hartnett, Sabina. (2019). Willkommenskultur: A Computational and Socio-linguistic Study of Modern German Discourse on Migrant Populations. Transit, 12(1). Retrieved from: http://www.escholarship.org/uc/item/1x84x67r (2019)
|
|
BASE
|
|
Show details
|
|
32 |
COMPARING SOLUTIONS TO THE LINKING PROBLEM USING AN INTEGRATED QUANTITATIVE FRAMEWORK OF LANGUAGE ACQUISITION
|
|
|
|
In: LANGUAGE, vol 95, iss 4 (2019)
|
|
BASE
|
|
Show details
|
|
33 |
Modeling Language Variation and Universals: A Survey on Typological Linguistics for Natural Language Processing
|
|
|
|
In: ISSN: 0891-2017 ; EISSN: 1530-9312 ; Computational Linguistics ; https://hal.archives-ouvertes.fr/hal-02425462 ; Computational Linguistics, Massachusetts Institute of Technology Press (MIT Press), 2019, 45 (3), pp.559-601. ⟨10.1162/coli_a_00357⟩ ; https://www.mitpressjournals.org/doi/abs/10.1162/coli_a_00357 (2019)
|
|
BASE
|
|
Show details
|
|
34 |
Modelling the Semantic Change Dynamics using Diachronic Word Embedding
|
|
|
|
In: 11th International Conference on Agents and Artificial Intelligence (NLPinAI Special Session) ; https://hal.archives-ouvertes.fr/hal-02048377 ; 11th International Conference on Agents and Artificial Intelligence (NLPinAI Special Session), Feb 2019, Prague, Czech Republic (2019)
|
|
BASE
|
|
Show details
|
|
35 |
Mining Discourse Markers for Unsupervised Sentence Representation Learning
|
|
|
|
In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) ; Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL 2019) ; https://hal.archives-ouvertes.fr/hal-02397473 ; Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL 2019), Jun 2019, Minneapolis, United States. pp.3477-3486 (2019)
|
|
BASE
|
|
Show details
|
|
36 |
Detecting Incoherence Requirements in Large Documents
|
|
|
|
In: Requirements Engineering Magazine ; https://hal.archives-ouvertes.fr/hal-03003826 ; Requirements Engineering Magazine, 2019, 12 (4), pp.(electronic medium) ; https://re-magazine.ireb.org/articles/detecting-incoherent-requirements-in-large-documents-experiments-and-user-evaluation (2019)
|
|
BASE
|
|
Show details
|
|
37 |
Adaptation and Implementation of the ISO42010 Standard to Software Design and Modeling Tools
|
|
|
|
In: Model-Driven Engineering and Software Development. MODELSWARD 2018, Communications in Computer and Information Science ; https://hal-cea.archives-ouvertes.fr/cea-02572737 ; Model-Driven Engineering and Software Development. MODELSWARD 2018, Communications in Computer and Information Science, pp.236-258, 2019, ⟨10.1007/978-3-030-11030-7_11⟩ (2019)
|
|
BASE
|
|
Show details
|
|
38 |
An LSTM-Based Neural Network Architecture for Model Transformations
|
|
|
|
In: 2019 ACM/IEEE 22nd International Conference on Model Driven Engineering Languages and Systems (MODELS) ; https://hal-cea.archives-ouvertes.fr/cea-02572669 ; 2019 ACM/IEEE 22nd International Conference on Model Driven Engineering Languages and Systems (MODELS), Sep 2019, Munich, Germany. pp.294-299, ⟨10.1109/MODELS.2019.00013⟩ (2019)
|
|
BASE
|
|
Show details
|
|
39 |
Preface to MDE Intelligence 2019: 1st Workshop on Artificial Intelligence and Model-Driven Engineering
|
|
|
|
In: 2019 ACM/IEEE 22nd International Conference on Model Driven Engineering Languages and Systems Companion (MODELS-C) ; https://hal-cea.archives-ouvertes.fr/cea-02572659 ; 2019 ACM/IEEE 22nd International Conference on Model Driven Engineering Languages and Systems Companion (MODELS-C), Sep 2019, Munich, Germany. pp.168-169, ⟨10.1109/MODELS-C.2019.00028⟩ (2019)
|
|
BASE
|
|
Show details
|
|
40 |
The Future of Model Transformation Languages: An Open Community Discussion.
|
|
|
|
In: ISSN: 1660-1769 ; The Journal of Object Technology ; https://hal-cea.archives-ouvertes.fr/cea-02572743 ; The Journal of Object Technology, Chair of Software Engineering, 2019, 18 (3), pp.7:1. ⟨10.5381/jot.2019.18.3.a7⟩ (2019)
|
|
BASE
|
|
Show details
|
|
|
|