| 10 |
Potential of Dedicated Language Processing Units in Computer Voice Interaction
|
|
|
|
In: Idaho Conference on Undergraduate Research (2017)
|
|
BASE
|
|
Show details
|
|
|
| 11 |
An outline of type-theoretical approaches to lexical semantics
|
|
|
|
In: ISSN: 2299-856X ; EISSN: 2299-8470 ; Journal of Language Modelling ; https://hal.archives-ouvertes.fr/hal-01802968 ; Journal of Language Modelling, Institute of Computer Science, Polish Academy of Sciences, Poland, 2017, 5 (2), pp.165-178. ⟨10.15398/jlm.v5i2.200⟩ (2017)
|
|
BASE
|
|
Show details
|
|
|
| 12 |
Classifiers, Sorts, and Base Types in the Montagovian Generative Lexicon and Related Type Theoretical Frameworks for Lexical Compositional Semantics
|
|
|
|
In: Modern Perspectives in Type-Theoretical Semantics ; https://hal.archives-ouvertes.fr/hal-01471256 ; Modern Perspectives in Type-Theoretical Semantics, Studies in Linguistics and Philosophy (98), pp.163-188, 2017, 978-3-319-50422-3. ⟨10.1007/978-3-319-50422-3_7⟩ (2017)
|
|
BASE
|
|
Show details
|
|
|
| 13 |
СОСТАВ И СТРУКТУРА КОРПУСА ТЕКСТОВ RUSSIAN DECEPTION BANK, ПРЕДНАЗНАЧЕННОГО ДЛЯ РАЗРАБОТКИ МЕТОДИК ДИАГНОСТИРОВАНИЯ ЛЖИ В РЕЧИ
|
|
|
|
BASE
|
|
Show details
|
|
|
| 14 |
Domain adaptation for statistical machine translation and neural machine translation
|
|
Zhang, Jian. - : Dublin City University. School of Computing, 2017. : Dublin City University. ADAPT, 2017
|
|
In: Zhang, Jian orcid:0000-0001-5659-5865 (2017) Domain adaptation for statistical machine translation and neural machine translation. PhD thesis, Dublin City University. (2017)
|
|
BASE
|
|
Show details
|
|
|
| 15 |
Detection of verbal multi-word expressions via conditional random fields with syntactic dependency features and semantic re-ranking
|
|
|
|
In: Maldonado, Alfredo orcid:0000-0001-8426-5249 , Han, Lifeng orcid:0000-0002-3221-2185 , Moreau, Erwan orcid:0000-0001-7692-526X , Alsulaimani, Ashjan, Chowdhury, Koel, Vogel, Carl orcid:0000-0001-8928-8546 and Liu, Qun orcid:0000-0002-7000-1792 (2017) Detection of verbal multi-word expressions via conditional random fields with syntactic dependency features and semantic re-ranking. In: 13th Workshop on Multiword Expressions (MWE 2017), Apr 2017, Valencia, Spain. (2017)
|
|
BASE
|
|
Show details
|
|
|
| 16 |
Incorporating visual information into neural machine translation
|
|
Calixto, Iacer. - : Dublin City University. School of Computing, 2017. : Dublin City University. ADAPT, 2017
|
|
In: Calixto, Iacer (2017) Incorporating visual information into neural machine translation. PhD thesis, Dublin City University. (2017)
|
|
BASE
|
|
Show details
|
|
|
| 17 |
Dublin City University participation in the VTT track at TRECVid 2017
|
|
|
|
In: Afli, Haithem orcid:0000-0002-7449-4707 , Hu, Feiyan orcid:0000-0001-7451-6438 , Du, Jinhua orcid:0000-0002-3267-4881 , Cosgrove, Daniel, McGuinness, Kevin orcid:0000-0003-1336-6477 , O'Connor, Noel E. orcid:0000-0002-4033-9135 , Arazo Sánchez, Eric, Zhou, Jiang orcid:0000-0002-3067-8512 and Smeaton, Alan F. orcid:0000-0003-1028-8389 (2017) Dublin City University participation in the VTT track at TRECVid 2017. In: TRECVid workshop, 13-15 Nov 2017, Gaithersburg, Md., USA. (2017)
|
|
BASE
|
|
Show details
|
|
|
| 18 |
Machine translation of morphologically rich languages using deep neural networks
|
|
Passban, Peyman. - : Dublin City University. School of Computing, 2017. : Dublin City University. ADAPT, 2017
|
|
In: Passban, Peyman (2017) Machine translation of morphologically rich languages using deep neural networks. PhD thesis, Dublin City University. (2017)
|
|
Abstract:
This thesis addresses some of the challenges of translating morphologically rich languages (MRLs). Words in MRLs have more complex structures than those in other languages, so that a word can be viewed as a hierarchical structure with several internal subunits. Accordingly, word-based models in which words are treated as atomic units are not suitable for this set of languages. As a commonly used and eff ective solution, morphological decomposition is applied to segment words into atomic and meaning-preserving units, but this raises other types of problems some of which we study here. We mainly use neural networks (NNs) to perform machine translation (MT) in our research and study their diff erent properties. However, our research is not limited to neural models alone as we also consider some of the difficulties of conventional MT methods. First we try to model morphologically complex words (MCWs) and provide better word-level representations. Words are symbolic concepts which are represented numerically in order to be used in NNs. Our first goal is to tackle this problem and find the best representation for MCWs. In the next step we focus on language modeling (LM) and work at the sentence level. We propose new morpheme-segmentation models by which we finetune existing LMs for MRLs. In this part of our research we try to find the most efficient neural language model for MRLs. After providing word- and sentence-level neural information in the first two steps, we try to use such information to enhance the translation quality in the statistical machine translation (SMT) pipeline using several diff erent models. Accordingly, the main goal in this part is to find methods by which deep neural networks (DNNs) can improve SMT. One of the main interests of the thesis is to study neural machine translation (NMT) engines from diff erent perspectives, and finetune them to work with MRLs. In the last step we target this problem and perform end-to-end sequence modeling via NN-based models. NMT engines have recently improved significantly and perform as well as state-of-the-art systems, but still have serious problems with morphologically complex constituents. This shortcoming of NMT is studied in two separate chapters in the thesis, where in one chapter we investigate the impact of diff erent non-linguistic morpheme-segmentation models on the NMT pipeline, and in the other one we benefit from a linguistically motivated morphological analyzer and propose a novel neural architecture particularly for translating from MRLs. Our overall goal for this part of the research is to find the most suitable neural architecture to translate MRLs. We evaluated our models on diff erent MRLs such as Czech, Farsi, German, Russian, and Turkish, and observed significant improvements. The main goal targeted in this research was to incorporate morphological information into MT and define architectures which are able to model the complex nature of MRLs. The results obtained from our experimental studies confirm that we were able to achieve our goal.
|
|
Keyword:
Computational linguistics; Machine learning; Machine translating
|
|
URL: http://doras.dcu.ie/22200/
|
|
BASE
|
|
Hide details
|
|
|
| 19 |
Entity linking for Tweets
|
|
|
|
In: Basile, Pierpaolo orcid:0000-0002-0545-1105 and Caputo, Annalina orcid:0000-0002-7144-8545 (2017) Entity linking for Tweets. Encyclopedia with Semantic Computing and Robotic Intelligence, 1 (1). pp. 1-9. ISSN 2529-7376 (2017)
|
|
BASE
|
|
Show details
|
|
|
| 20 |
How do users perceive information: analyzing user feedback while annotating textual units
|
|
|
|
In: Arora, Piyush orcid:0000-0003-0055-345X and Jones, Gareth J.F. orcid:0000-0003-2923-8365 (2017) How do users perceive information: analyzing user feedback while annotating textual units. In: CHIIR 2017 Workshop on Supporting Complex Search Tasks, 11 Mar 2017, Oslo, Norway. (2017)
|
|
BASE
|
|
Show details
|
|
|
|
|
