1 |
Improving the performance of an example-based machine translation system using a domain-specific bilingual lexicon
|
|
|
|
In: 29th Pacific Asia Conference on Language, Information and Computation, PACLIC 2015 ; https://hal-cea.archives-ouvertes.fr/cea-01844060 ; 29th Pacific Asia Conference on Language, Information and Computation, PACLIC 2015, Oct 2015, Shangai, China. pp.106-115 (2015)
|
|
BASE
|
|
Show details
|
|
2 |
Evaluating the impact of using a domain-specific bilingual lexicon on the performance of a hybrid machine translation approach
|
|
|
|
In: 10th International Conference on Recent Advances in Natural Language Processing, RANLP 201 ; https://hal-cea.archives-ouvertes.fr/cea-01844051 ; 10th International Conference on Recent Advances in Natural Language Processing, RANLP 201, Sep 2015, Hissar, Bulgaria. pp.579-587 (2015)
|
|
BASE
|
|
Show details
|
|
3 |
Systematic generation of standard compliant tool support of diagrammatic modeling languages
|
|
|
|
In: 2015 ACM/IEEE 18th International Conference on Model Driven Engineering Languages and Systems (MODELS) ; https://hal-cea.archives-ouvertes.fr/cea-01836563 ; 2015 ACM/IEEE 18th International Conference on Model Driven Engineering Languages and Systems (MODELS), Sep 2015, Ottawa, Canada. pp.348-357, ⟨10.1109/MODELS.2015.7338266⟩ (2015)
|
|
BASE
|
|
Show details
|
|
4 |
Handwritten word recognition using Web resources and recurrent neural networks
|
|
|
|
In: International Journal on Document Analysis and Recognition ; https://hal.archives-ouvertes.fr/hal-01845537 ; International Journal on Document Analysis and Recognition, 2015, 18 (4), pp.287-301. ⟨10.1007/s10032-015-0251-1⟩ (2015)
|
|
Abstract:
International audience ; Handwriting recognition systems usually rely on static dictionaries and language models. Full coverage of these dictionaries is generally not achieved when dealing with unrestricted document corpora due to the presence of Out-Of-Vocabulary (OOV) words. We propose an approach which uses the World Wide Web as a corpus to improve dictionary coverage. We exploit the very large and freely available Wikipedia corpus in order to obtain dynamic dictionaries on the fly. We rely on recurrent neural network (RNN) recognizers, with and without linguistic resources, to detect words that are non-reliably recognized within a word sequence. Such words are labeled as non-anchor words (NAWs) and include OOVs and In-Vocabulary words recognized with low confidence. To recognize a non-anchor word, a dynamic dictionary is built by selecting words from the Web resource based on their string similarity with the NAW image, and their linguistic relevance in the NAW context. Similarity is evaluated by computing the edit distance between the sequence of characters generated by the RNN recognizer exploited as a filler model, and the Wikipedia words. Linguistic relevance is based on an N-gram language model estimated from the Wikipedia corpus. Experiments conducted on aword-segmented version of the publicly available RIMES database show that the proposed approach can improve recognition accuracy compared to systems based on static dictionaries only. The proposed approach shows even better behavior as the proportion of OOVs increases, in terms of both accuracy and dictionary coverage.
|
|
Keyword:
[INFO]Computer Science [cs]; Character recognition; Computational linguistics; Dynamic dictionaries; Handwriting recognition; Handwritten word recognition; Linguistic resources; Linguistics; N-gram language models; Out of vocabulary words; Recurrent neural network (RNN); Recurrent neural networks; Vocabulary control; Web resources; World Wide Web
|
|
URL: https://hal.archives-ouvertes.fr/hal-01845537 https://doi.org/10.1007/s10032-015-0251-1
|
|
BASE
|
|
Hide details
|
|
5 |
Introduction to ACESMB 2015- Model-based architecting of cyber-physical and embedded systems
|
|
|
|
In: 8th Joint International Workshop on Model-Based Architecting of Cyber-Physical and Embedded Systems and 1st International Workshop on UML Consistency Rules, ACES-MB 2015 and WUCOR 2015 ; https://hal-cea.archives-ouvertes.fr/cea-01844050 ; 8th Joint International Workshop on Model-Based Architecting of Cyber-Physical and Embedded Systems and 1st International Workshop on UML Consistency Rules, ACES-MB 2015 and WUCOR 2015, Sep 2015, Ottawa, Canada. pp.1-2 (2015)
|
|
BASE
|
|
Show details
|
|
6 |
Fast as a shadow, expressive as a tree: Hybrid memory monitoring for C.
|
|
|
|
In: SAC '15 Proceedings of the 30th Annual ACM Symposium on Applied Computing ; https://hal-cea.archives-ouvertes.fr/cea-01836267 ; SAC '15 Proceedings of the 30th Annual ACM Symposium on Applied Computing, Apr 2015, Salamanca, Spain. pp.1765-1772, ⟨10.1145/2695664.2695815⟩ (2015)
|
|
BASE
|
|
Show details
|
|
7 |
Generative event schema induction with entity disambiguation
|
|
|
|
In: Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing ; https://hal-cea.archives-ouvertes.fr/cea-01844047 ; Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing, Jul 2015, Beijing, China. pp.188-197 (2015)
|
|
BASE
|
|
Show details
|
|
8 |
Tool paper: Combining Alf and UML in modeling tools: An example with papyrus
|
|
|
|
In: 15th International Workshop on OCL and Textual Modeling, OCL 2015 ; https://hal-cea.archives-ouvertes.fr/cea-01844056 ; 15th International Workshop on OCL and Textual Modeling, OCL 2015, Sep 2015, Ottawa, Canada. pp.105-119 (2015)
|
|
BASE
|
|
Show details
|
|
9 |
BLSTM-based handwritten text recognition using Web resources
|
|
|
|
In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR) ; https://hal-cea.archives-ouvertes.fr/cea-01841169 ; 2015 13th International Conference on Document Analysis and Recognition (ICDAR), Aug 2015, Tunis, Tunisia. pp.466-470, ⟨10.1109/ICDAR.2015.7333805⟩ (2015)
|
|
BASE
|
|
Show details
|
|
10 |
Early and late combinations of criteria for reranking distributional thesauri
|
|
|
|
In: Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Short Papers) ; https://hal-cea.archives-ouvertes.fr/cea-01844049 ; Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Short Papers), Jul 2015, Beijing, China. pp.470-476 (2015)
|
|
BASE
|
|
Show details
|
|
|
|