| 2 |
Planning Human-Computer Improvisation
|
|
|
|
In: International Computer Music Conference ; https://hal.archives-ouvertes.fr/hal-01053834 ; International Computer Music Conference, Sep 2014, Athens, Greece ; http://icmc14-smc14.net (2014)
|
|
BASE
|
|
Show details
|
|
|
| 3 |
Arabic Language Text Classification Using Dependency Syntax-Based Feature Selection
|
|
|
|
In: Proceedings CITALA 2014 : 5ème Conférence Internationale sur le Traitement Automatique de la Langue Arabe ; CITALA 2014 : 5ème Conférence Internationale sur le Traitement Automatique de la Langue Arabe ; https://hal.archives-ouvertes.fr/hal-01185094 ; CITALA 2014 : 5ème Conférence Internationale sur le Traitement Automatique de la Langue Arabe, Nov 2014, Oujda, Morocco. pp.31 - 40 (2014)
|
|
BASE
|
|
Show details
|
|
|
| 4 |
Using Function Words for Authorship Attribution: Bag-Of-Words vs. Sequential Rules
|
|
|
|
In: Natural Language Processing and Cognitive Science Proceedings 2014 ; The 11th International Workshop on Natural Language Processing and Cognitive Science ; https://hal.sorbonne-universite.fr/hal-01198407 ; The 11th International Workshop on Natural Language Processing and Cognitive Science, Oct 2014, Venice, Italy. pp.115-122, ⟨10.1515/9781501501289.115⟩ (2014)
|
|
BASE
|
|
Show details
|
|
|
| 5 |
A perceptual-to-conceptual gradient of word coding along the ventral path
|
|
|
|
In: PRNI 2014 - 4th International Workshop on Pattern Recognition in NeuroImaging ; https://hal.inria.fr/hal-00986606 ; PRNI 2014 - 4th International Workshop on Pattern Recognition in NeuroImaging, Jun 2014, Tubingen, Germany (2014)
|
|
BASE
|
|
Show details
|
|
|
| 6 |
Homogenous and heterogeneous logical proportions
|
|
|
|
In: ISSN: 0955-792X ; EISSN: 1465-363X ; Journal of Logic and Computation ; https://hal.archives-ouvertes.fr/hal-01154243 ; Journal of Logic and Computation, Oxford University Press (OUP), 2014, Vol. 1 (n° 1), pp. 1-52 (2014)
|
|
BASE
|
|
Show details
|
|
|
| 7 |
Probabilistic Cognitive Maps Semantics of a Cognitive Map when the Values are Assumed to be Probabilities
|
|
|
|
In: International Conference on Agents and Artificial Intelligence (ICAART) ; https://hal.archives-ouvertes.fr/hal-00957935 ; International Conference on Agents and Artificial Intelligence (ICAART), 2014, Angers, France. pp.52-62 (2014)
|
|
BASE
|
|
Show details
|
|
|
| 9 |
PREDICTING MUSIC GENRE PREFERENCES BASED ON ONLINE COMMENTS
|
|
|
|
In: Master's Theses (2014)
|
|
BASE
|
|
Show details
|
|
|
| 10 |
DisMo: A Morphosyntactic, Disfluency and Multi-Word Unit Annotator. An Evaluation on a Corpus of French Spontaneous and Read Speech
|
|
|
|
In: Proceedings of the 9th International Conference on Language Resources and Evaluation (LREC) ; https://hal.archives-ouvertes.fr/hal-01703495 ; Proceedings of the 9th International Conference on Language Resources and Evaluation (LREC), May 2014, Reykjavik, Iceland (2014)
|
|
BASE
|
|
Show details
|
|
|
| 11 |
Phrase extraction and rescoring in statistical machine translation
|
|
Srivastava, Ankit Kumar. - : Dublin City University. Centre for Next Generation Localisation (CNGL), 2014. : Dublin City University. School of Computing, 2014
|
|
In: Srivastava, Ankit Kumar (2014) Phrase extraction and rescoring in statistical machine translation. PhD thesis, Dublin City University. (2014)
|
|
Abstract:
The lack of linguistically motivated translation units or phrase pairs in Phrase-based Statistical Machine Translation (PB-SMT) systems is a well-known source of error. One approach to minimise such errors is to supplement the standard PB-SMT models with phrase pairs extracted from parallel treebanks (linguistically annotated and aligned corpora). In this thesis, we extend the treebank-based phrase extraction framework with percolated dependencies – a hitherto unutilised knowledge source – and evaluate its usability through more than a dozen syntax-aware phrase extraction models. However, the improvement in system performance is neither consistent nor conclusive despite the proven advantages of linguistically motivated phrase pairs. This leads us to hypothesize that the PB-SMT pipeline is flawed as it often fails to access perfectly good phrase-pairs while searching for the highest scoring translation (decoding). A model error occurs when the highest-probability translation (actual output of a PB-SMT system) according to a statistical machine translation model is not the most accurate translation it can produce. In the second part of this thesis, we identify and attempt to trace these model errors across state-of-the-art PB-SMT decoders by locating the position of oracle translations (the translation most similar to a reference translation or expected output of a PB-SMT system) in the n-best lists generated by a PB-SMT decoder. We analyse the impact of individual decoding features on the quality of translation output and introduce two rescoring algorithms to minimise the lower ranking of oracles in the n-best lists. Finally, we extend our oracle-based rescoring approach to a reranking framework by rescoring the n-best lists with additional reranking features. We observe limited but optimistic success and conclude by speculating on how our oracle-based rescoring of n-best lists can help the PB-SMT system (supplemented with multiple treebank-based phrase extractions) get optimal performance out of linguistically motivated phrase pairs.
|
|
Keyword:
Computational linguistics; Machine learning; Machine translating; Phrase-based Statistical Machine Translation (PB-SMT) systems; Treebank-based phrase extraction framework
|
|
URL: http://doras.dcu.ie/19971/
|
|
BASE
|
|
Hide details
|
|
|
| 12 |
Code mixing: a challenge for language identification in the language of social media
|
|
|
|
In: Barman, Utsab, Das, Amitava orcid:0000-0003-3418-463X , Wagner, Joachim orcid:0000-0002-8290-3849 and Foster, Jennifer orcid:0000-0002-7789-4853 (2014) Code mixing: a challenge for language identification in the language of social media. In: First Workshop on Computational Approaches to Code Switching, 25 Oct 2014, Doha, Qatar. (2014)
|
|
BASE
|
|
Show details
|
|
|
| 13 |
A new multi-modal dataset for human affect analysis
|
|
|
|
In: Wei, Haolin, Monaghan, David orcid:0000-0002-5169-9902 , O'Connor, Noel E. orcid:0000-0002-4033-9135 and Scanlon, Patricia (2014) A new multi-modal dataset for human affect analysis. In: Human Behavior Understanding 5th International Workshop, HBU 2014, 12 Sept 2014, Zurich, Switzerland. (2014)
|
|
BASE
|
|
Show details
|
|
|
| 14 |
Referential translation machines for predicting translation quality
|
|
|
|
In: Bicici, Ergun and Way, Andy orcid:0000-0001-5736-5930 (2014) Referential translation machines for predicting translation quality. In: ACL 2014 9th workshop on statistical machine translation, 26-27 June 2014, Baltimore, USA. (2014)
|
|
BASE
|
|
Show details
|
|
|
| 15 |
RTM-DCU: referential translation machines for semantic similarity
|
|
|
|
In: Bicici, Ergun and Way, Andy orcid:0000-0001-5736-5930 (2014) RTM-DCU: referential translation machines for semantic similarity. In: SemEval-2014: Semantic Evaluation Exercises - International Workshop on Semantic Evaluation, 23-24 Aug 2014, DCU, Dublin, Ireland. (2014)
|
|
BASE
|
|
Show details
|
|
|
| 16 |
Boosting bonsai trees for efficient features combination : application to speaker role identification
|
|
|
|
In: Interspeech ; https://hal.inria.fr/hal-01025171 ; Interspeech, Sep 2014, Singapour, Singapore (2014)
|
|
BASE
|
|
Show details
|
|
|
| 17 |
Splitting Arabic Texts into Elementary Discourse Units
|
|
|
|
In: ISSN: 1530-0226 ; ACM Transactions on Asian Language Information Processing ; https://hal.archives-ouvertes.fr/hal-01120621 ; ACM Transactions on Asian Language Information Processing, Association for Computing Machinery, 2014, vol. 13 (n° 2), pp. 1-23. ⟨10.1145/2601401⟩ (2014)
|
|
BASE
|
|
Show details
|
|
|
| 18 |
Senso Comune as a Knowledge Base of Italian language: The Resource and its Development
|
|
|
|
In: Proceedings of the First Italian Conference on Computational Linguistics CLiC-it 2014 ; First Italian Conference on Computational Linguistics - CLiC-it 2014 ; https://hal.archives-ouvertes.fr/hal-01134621 ; First Italian Conference on Computational Linguistics - CLiC-it 2014, Dec 2014, Pisa, Italy. pp. 93-97 (2014)
|
|
BASE
|
|
Show details
|
|
|
| 19 |
Selectional Restrictions, Types and Categories
|
|
|
|
In: ISSN: 1570-8683 ; Journal of Applied Logic ; https://hal.archives-ouvertes.fr/hal-01123735 ; Journal of Applied Logic, Elsevier, 2014, vol. 12 (n° 1), pp. 75-87. ⟨10.1016/j.jal.2013.08.002⟩ (2014)
|
|
BASE
|
|
Show details
|
|
|
| 20 |
OntoEnrich: A Platform for the Lexical Analysis of Ontologies
|
|
|
|
In: Knowledge Engineering and Knowledge Management ; 19th International Conference on Knowledge Engineering and Knowledge Management - EKAW 2014 Satellite Events (EKAW 2014) ; https://hal.archives-ouvertes.fr/hal-01363345 ; 19th International Conference on Knowledge Engineering and Knowledge Management - EKAW 2014 Satellite Events (EKAW 2014), Nov 2014, Linköping, Sweden. pp. 172-176 (2014)
|
|
BASE
|
|
Show details
|
|
|
|
|
