101 |
Learning morphology with Morfette
|
|
|
|
In: Chrupała, Grzegorz, Dinu, Georgiana and van Genabith, Josef (2008) Learning morphology with Morfette. In: LREC 2008 - Sixth International Conference on Language Resources and Evaluation, 28-30 May 2008, Marrakech, Morocco. (2008)
|
|
BASE
|
|
Show details
|
|
102 |
Dublin City University at QA@CLEF 2008
|
|
|
|
In: Adafre, Sisay Fissaha and van Genabith, Josef (2008) Dublin City University at QA@CLEF 2008. In: CLEF 2008 - 9th Workshop of the Cross-Language Evaluation Forum, 17-19 September, 2008, Aarhus, Denmark. ISBN 978-3-642-04446-5 (2008)
|
|
BASE
|
|
Show details
|
|
103 |
Dependency-based n-gram models for general purpose sentence realisation
|
|
|
|
In: Guo, Yuqing, van Genabith, Josef and Wang, Haifeng (2008) Dependency-based n-gram models for general purpose sentence realisation. In: COLING 2008 - 22nd International Conference on Computational Linguistics, 18-22 August 2008, Manchester, UK. (2008)
|
|
BASE
|
|
Show details
|
|
104 |
Parser-based retraining for domain adaptation of probabilistic generators
|
|
|
|
In: Hogan, Deirdre, Foster, Jennifer orcid:0000-0002-7789-4853 , Wagner, Joachim orcid:0000-0002-8290-3849 and van Genabith, Josef (2008) Parser-based retraining for domain adaptation of probabilistic generators. In: INLG 08 - 5th International Natural Language Generation Conference, 12-14 June 2008, Salt Fork, Ohio, USA. (2008)
|
|
BASE
|
|
Show details
|
|
105 |
Recovering non-local dependencies for Chinese
|
|
|
|
In: Guo, Yuqing, Wang, Haifeng and van Genabith, Josef (2007) Recovering non-local dependencies for Chinese. In: EMNLP-CoNLL 2007 - Joint Meeting of the Conference on Empirical Methods in Natural Language Processing and the Conference on Computational Natural Language Learning, 28-30 June 2007, Prague, Czech Republic. (2007)
|
|
BASE
|
|
Show details
|
|
106 |
Preparing, restructuring, and augmenting a French treebank: lexicalised parsers or coherent treebanks?
|
|
|
|
In: Schluter, Natalie and van Genabith, Josef (2007) Preparing, restructuring, and augmenting a French treebank: lexicalised parsers or coherent treebanks? In: PACLING 2007 - 10th Conference of the Pacific Association for Computational Linguistics, 19-21 September , 2007, Melbourne, Australia. (2007)
|
|
BASE
|
|
Show details
|
|
107 |
Treebank-based acquisition of LFG resources for Chinese
|
|
|
|
In: Guo, Yuqing, van Genabith, Josef and Wang, Haifeng (2007) Treebank-based acquisition of LFG resources for Chinese. In: Lexical Functional Grammar 2007, 28-30 July 2007, California, USA. (2007)
|
|
BASE
|
|
Show details
|
|
108 |
C-structures and f-structures for the British national corpus
|
|
|
|
In: Wagner, Joachim orcid:0000-0002-8290-3849 , Seddah, Djamé, Foster, Jennifer orcid:0000-0002-7789-4853 and van Genabith, Josef (2007) C-structures and f-structures for the British national corpus. In: Lexical Functional Grammar 2007, 28-30 July 2007, California, USA. (2007)
|
|
BASE
|
|
Show details
|
|
109 |
TransBooster:black box optimisation of machine translation systems
|
|
|
|
In: Mellebeek, Bart (2007) TransBooster:black box optimisation of machine translation systems. PhD thesis, Dublin City University. (2007)
|
|
Abstract:
Machine Translation (MT) systems tend to underperform when faced with long, linguistically complex sentences. Rule-based systems often trade a broad but shallow linguistic coverage for a deep, fine-grained analysis since hand-crafting rules based on detailed linguistic analyses is time-consuming, error-prone and expensive. Most datadriven systems lack the necessary syntactic knowledge to effectively deal with non-local grammatical phenomena. Therefore, both rule-based and data-driven MT systems are better at handling short, simple sentences than linguistically complex ones. This thesis proposes a new and modular approach to help MT systems improve then output quality by reducing the number of complexities in the input. Instead of trying to reinvent the wheel by proposing yet another approach to MT, we build on the strengths of existing MT paradigms while trying to remedy their shortcomings as much as possible. We do this by developing TransBooster, a wrapper technology that reduces the complexity of the MT input by a recursive decomposition algorithm which produces simple input chunks that are spoon-fed to a baseline MT system TransBooster is not an MT system itself: it does not perform automatic translation, but operates on top of an existing MT system, gulding it through the input and trying to help the baseline system to improve the quality of its own translations through automatic complexity reduction. In this dissertation, we outline the motivation behind TransBooster, explain its development in depth and investigate its impact on the three most important paradigms in the field Rule-based, Example-based and Statistical MT. In addition, we use the Trans-Booster architecture as a promising alternative to current Multi-Engine MT techniques. We evaluate TransBooster on the language pair Engl~sh-+Spanish with a combination of automatic and manual evaluation metrics, prov~ding a rigorous analysis of the potential and shortcomings of our approach.
|
|
Keyword:
example based mt; Machine translating; machine translation; statistical mt; tule based mt
|
|
URL: http://doras.dcu.ie/16939/
|
|
BASE
|
|
Hide details
|
|
110 |
Dependency-based automatic evaluation for machine translation
|
|
|
|
In: Owczarzak, Karolina, van Genabith, Josef and Way, Andy orcid:0000-0001-5736-5930 (2007) Dependency-based automatic evaluation for machine translation. In: HLT-NAACL 2007 - Workshop on Syntax and Structure in Statistical Translation, 26 April 2007, Rochester, New York, USA. (2007)
|
|
BASE
|
|
Show details
|
|
111 |
Labelled dependencies in machine translation evaluation
|
|
|
|
In: Owczarzak, Karolina, van Genabith, Josef and Way, Andy orcid:0000-0001-5736-5930 (2007) Labelled dependencies in machine translation evaluation. In: ACL 2007 Workshop on Statistical Machine Translation, 23 June 2007, Prague, Czech Republic. (2007)
|
|
BASE
|
|
Show details
|
|
112 |
Using very large corpora to detect raising and control verbs
|
|
|
|
In: Chrupała, Grzegorz and van Genabith, Josef (2007) Using very large corpora to detect raising and control verbs. In: Lexical Functional Grammar 2007, 28-30 July 2007, California, USA. (2007)
|
|
BASE
|
|
Show details
|
|
113 |
Using F-structures in machine translation evaluation
|
|
|
|
In: Owczarzak, Karolina, van Genabith, Josef, Graham, Yvette and Way, Andy orcid:0000-0001-5736-5930 (2007) Using F-structures in machine translation evaluation. In: Lexical Functional Grammar 2007, 28-30 July 2007, California, USA. (2007)
|
|
BASE
|
|
Show details
|
|
114 |
Exploiting multi-word units in history-based probabilistic generation
|
|
|
|
In: Hogan, Deirdre, Cafferkey, Conor, Cahill, Aoife orcid:0000-0002-3519-7726 and van Genabith, Josef (2007) Exploiting multi-word units in history-based probabilistic generation. In: EMNLP-CoNLL 2007 - Joint Meeting of the Conference on Empirical Methods in Natural Language Processing and the Conference on Computational Natural Language Learning, 28-30 June 2007, Prague, Czech Republic. (2007)
|
|
BASE
|
|
Show details
|
|
115 |
Design, development, implementation and evaluation of a purilingual ICALL system for romance languages aimed at advanced learners
|
|
|
|
In: Koller, Thomas (2007) Design, development, implementation and evaluation of a purilingual ICALL system for romance languages aimed at advanced learners. PhD thesis, Dublin City University. (2007)
|
|
BASE
|
|
Show details
|
|
116 |
The integration of CL resources in CALL for Irish in the primary school context
|
|
Ward, Monica. - : Dublin City University. School of Computing, 2007
|
|
In: Ward, Monica (2007) The integration of CL resources in CALL for Irish in the primary school context. PhD thesis, Dublin City University. (2007)
|
|
BASE
|
|
Show details
|
|
117 |
Adapting WSJ-trained parsers to the British national corpus using in-domain self-training
|
|
|
|
In: Foster, Jennifer orcid:0000-0002-7789-4853 , Wagner, Joachim orcid:0000-0002-8290-3849 , Seddah, Djamé and van Genabith, Josef (2007) Adapting WSJ-trained parsers to the British national corpus using in-domain self-training. In: IWPT 2007 - 10th International Conference of Parsing Technology, 23-24 June 2007, Prague, Czech Republic. (2007)
|
|
BASE
|
|
Show details
|
|
118 |
A comparative evaluation of deep and shallow approaches to the automatic detection of common grammatical errors
|
|
|
|
In: Wagner, Joachim orcid:0000-0002-8290-3849 , Foster, Jennifer orcid:0000-0002-7789-4853 and van Genabith, Josef (2007) A comparative evaluation of deep and shallow approaches to the automatic detection of common grammatical errors. In: EMNLP-CoNLL 2007 - Joint Meeting of the Conference on Empirical Methods in Natural Language Processing and the Conference on Computational Natural Language Learning, 28-30 June 2007, Prague, Czech Republic. (2007)
|
|
BASE
|
|
Show details
|
|
119 |
Treebank annotation schemes and parser evaluation for German
|
|
|
|
In: Rehbein, Ines and van Genabith, Josef (2007) Treebank annotation schemes and parser evaluation for German. In: EMNLP-CoNLL 2007 - Joint Meeting of the Conference on Empirical Methods in Natural Language Processing and the Conference on Computational Natural Language Learning, 28-30 June 2007, Prague, Czech Republic. (2007)
|
|
BASE
|
|
Show details
|
|
120 |
Evaluating evaluation measures
|
|
|
|
In: Rehbein, Ines and van Genabith, Josef (2007) Evaluating evaluation measures. In: NODALIDA 2007 - 16th Nordic Conference on Computational Linguistic, 25-26 May 2007, Tartu, Estonia. (2007)
|
|
BASE
|
|
Show details
|
|
|
|