21 |
Translating pro-drop languages with reconstruction models
|
|
|
|
In: Wang, Longyue orcid:0000-0002-9062-6183 , Tu, Zhaopeng, Shi, Shuming, Zhang, Tong, Graham, Yvette and Liu, Qun orcid:0000-0002-7000-1792 (2018) Translating pro-drop languages with reconstruction models. In: 32nd AAAI Conference on Artificial Intelligence (AAAI 2018), 2 - 7 Feb 2018, New Orleans, LA, USA. ISBN 978-1-57735-800-8 (2018)
|
|
BASE
|
|
Show details
|
|
22 |
Promoting user engagement and learning in search tasks by effective document representation
|
|
Arora, Piyush. - : Dublin City University. School of Computing, 2018. : Dublin City University. ADAPT, 2018
|
|
In: Arora, Piyush orcid:0000-0002-4261-2860 (2018) Promoting user engagement and learning in search tasks by effective document representation. PhD thesis, Dublin City University. (2018)
|
|
BASE
|
|
Show details
|
|
23 |
Incorporating Chinese radicals into neural machine translation: deeper than character level
|
|
|
|
In: Han, Lifeng orcid:0000-0002-3221-2185 and Kuang, Shaohui (2018) Incorporating Chinese radicals into neural machine translation: deeper than character level. In: 30th European Summer School in Logic, Language and Information (ESSLLI 2018), 6-17 Aug 2018, Sofia, Bulgaria. (2018)
|
|
BASE
|
|
Show details
|
|
24 |
Evaluation of automatic video captioning using direct assessment
|
|
|
|
In: Graham, Yvette, Awad, George M. and Smeaton, Alan F. orcid:0000-0003-1028-8389 (2018) Evaluation of automatic video captioning using direct assessment. PLoS One . ISSN 1932-6203 (2018)
|
|
BASE
|
|
Show details
|
|
25 |
Incorporating Chinese radicals into neural machine translation: deeper Than character level
|
|
|
|
In: Han, Lifeng and Kuang, Shaohui (2018) Incorporating Chinese radicals into neural machine translation: deeper Than character level. In: 30th European Summer School in Logic, Language and Information (ESSLLI 2018), 6-17 Aug 2018, Sofia, Bulgaria. (2018)
|
|
Abstract:
In neural machine translation (NMT), researchers face the challenge of un-seen (or out-of-vocabulary OOV) words translation. To solve this, some researchers propose the splitting of western languages such as English and German into sub-words or compounds. In this paper, we try to address this OOV issue and improve the NMT adequacy with a harder language Chinese whose characters are even more sophisticated in composition. We integrate the Chinese radicals into the NMT model with different settings to address the unseen words challenge in Chinese to English translation. On the other hand, this also can be considered as semantic part of the MT system since the Chinese radicals usually carry the essential meaning of the words they are constructed in. Meaningful radicals and new characters can be integrated into the NMT systems with our models. We use an attention-based NMT system as a strong baseline system. The experiments on standard Chinese-to-English NIST translation shared task data 2006 and 2008 show that our designed models outperform the baseline model in a wide range of state-of-the-art evaluation metrics including LEPOR, BEER, and CharacTER, in addition to the traditional BLEU and NIST scores, especially on the adequacy-level translation. We also have some interesting findings from the results of our various experiment settings about the performance of words and characters in Chinese NMT, which is different with other languages. For instance, the fully character level NMT may perform very well or the state of the art in some other languages as researchers demonstrated recently, however, in the Chinese NMT model, word boundary knowledge is important for the model learning.
|
|
Keyword:
Algorithms; Artificial intelligence; Chinese decomposition; Chinese radical; Chinese to English Machine Translation; Computational linguistics; Computer software; Information technology; Linguistics; Machine learning; Machine translating
|
|
URL: http://doras.dcu.ie/24490/
|
|
BASE
|
|
Hide details
|
|
26 |
Apply Chinese radicals Into neural machine translation/ deeper than character level
|
|
|
|
In: Han, Lifeng orcid:0000-0002-3221-2185 (2018) Apply Chinese radicals Into neural machine translation/ deeper than character level. In: LPRC 2018: Limerick Postgraduate Research Conference, 24 May 2018, Limerick, Ireland. (2018)
|
|
BASE
|
|
Show details
|
|
27 |
Learning to represent, categorise and rank in community question answering
|
|
|
|
In: Bogdanova, Daria (2018) Learning to represent, categorise and rank in community question answering. PhD thesis, Dublin City University. (2018)
|
|
BASE
|
|
Show details
|
|
28 |
The balance between quantitative and qualitative literary stylistics: How the method of "motifs" can help
|
|
|
|
In: The Grammar of Genres and styles ; https://hal.archives-ouvertes.fr/hal-03546266 ; Legallois, Charnois, Larjavaara. The Grammar of Genres and styles, De Gruyter Mouton, 2018, 9783110589689. ⟨10.1515/9783110595864-008⟩ ; https://www-degruyter-com.ezproxy.univ-paris3.fr/document/doi/10.1515/9783110595864/html (2018)
|
|
BASE
|
|
Show details
|
|
29 |
Categorial Proof Nets and Dependency Locality: A New Metric for Linguistic Complexity
|
|
|
|
In: Symposium on Logic and Algorithms in Computational Linguistics ; LACompLing: Logic and Algorithms in Computational Linguistics ; https://hal-lirmm.ccsd.cnrs.fr/lirmm-01916104 ; LACompLing: Logic and Algorithms in Computational Linguistics, Aug 2018, Stockholm, Sweden. pp.73-86 ; http://staff.math.su.se/rloukanova/LACompLing2018-web/ (2018)
|
|
BASE
|
|
Show details
|
|
30 |
Cognitive science in the era of artificial intelligence: A roadmap for reverse-engineering the infant language-learner
|
|
|
|
In: ISSN: 0010-0277 ; EISSN: 1873-7838 ; Cognition ; https://hal.archives-ouvertes.fr/hal-01888694 ; Cognition, Elsevier, 2018, 173, pp.43 - 59. ⟨10.1016/j.cognition.2017.11.008⟩ (2018)
|
|
BASE
|
|
Show details
|
|
31 |
Explainable, Trustable and Emphatic Artificial Intelligence from Formal Argumentation Theory to Argumentation for Humans
|
|
|
|
In: https://hal.archives-ouvertes.fr/tel-01973555 ; Computer science. UNIVERSITÉ CÔTE D’AZUR, 2018 (2018)
|
|
BASE
|
|
Show details
|
|
32 |
Cohort effects and asymmetrical word-level sound change
|
|
|
|
In: Brendel, Christian Douglas. (2018). Cohort effects and asymmetrical word-level sound change. 0035: Linguistics. Retrieved from: http://www.escholarship.org/uc/item/9489q3fj (2018)
|
|
BASE
|
|
Show details
|
|
33 |
Modeling Events and Affects in Social Media Stories
|
|
|
|
In: Rahimtoroghi, Elahe. (2018). Modeling Events and Affects in Social Media Stories. UC Santa Cruz: Computer Science. Retrieved from: http://www.escholarship.org/uc/item/6tk1758v (2018)
|
|
BASE
|
|
Show details
|
|
34 |
An Algorithm for Learning Phonological Classes from Distributional Similarity
|
|
|
|
In: Mayer, Connor. (2018). An Algorithm for Learning Phonological Classes from Distributional Similarity. UCLA: Linguistics 0510. Retrieved from: http://www.escholarship.org/uc/item/5jp6q2xn (2018)
|
|
BASE
|
|
Show details
|
|
35 |
Separation and acquisition of two languages in early childhood : a multidisciplinary approach ; Séparation et acquisition de deux langues chez le jeune enfant : une approche pluridisciplinaire
|
|
|
|
In: https://tel.archives-ouvertes.fr/tel-03394824 ; Cognitive Sciences. Université Paris sciences et lettres, 2018. English. ⟨NNT : 2018PSLEE081⟩ (2018)
|
|
BASE
|
|
Show details
|
|
37 |
Prosodic and Pragmatic Values of Discourse Particles in French
|
|
|
|
In: ExLing 2018 - 9th Tutorial and Research Workshop on Experimental Linguistics ; https://hal.inria.fr/hal-01889925 ; ExLing 2018 - 9th Tutorial and Research Workshop on Experimental Linguistics, Aug 2018, Paris, France (2018)
|
|
BASE
|
|
Show details
|
|
38 |
Language, Cognition, and Computational Models
|
|
|
|
In: https://hal.archives-ouvertes.fr/hal-01722351 ; Cambridge University Press, 2018 ; https://www.cambridge.org/core/books/language-cognition-and-computational-models/90CC7DBA6CADB1FE361266D311CB4413 (2018)
|
|
BASE
|
|
Show details
|
|
39 |
Cognifying Model-Driven Software Engineering
|
|
|
|
In: Software Technologies: Applications and Foundations ; https://hal-cea.archives-ouvertes.fr/cea-02572650 ; Software Technologies: Applications and Foundations, pp.154-160, 2018, ⟨10.1007/978-3-319-74730-9_13⟩ (2018)
|
|
BASE
|
|
Show details
|
|
40 |
Boost your eHumanities and eHeritage research with Research Infrastructures (PARTHENOS Webinar)
|
|
|
|
In: https://hal.archives-ouvertes.fr/cel-01784097 ; 3rd cycle. Germany. 2018 (2018)
|
|
BASE
|
|
Show details
|
|
|
|