| 41 |
Segmenting and POS tagging Classical Tibetan using a memory-based tagger
|
|
|
|
In: Meelen, Marieke; & Hill, Nathan. (2017). Segmenting and POS tagging Classical Tibetan using a memory-based tagger. Himalayan Linguistics, 16(2). doi:10.5070/H916234501. Retrieved from: http://www.escholarship.org/uc/item/8b83z79n (2017)
|
|
BASE
|
|
Show details
|
|
|
| 45 |
Crowdsourcing lexical semantic judgements from bilingual dictionary users
|
|
|
|
BASE
|
|
Show details
|
|
|
| 46 |
Understanding Patterns in Infant-Directed Speech in Context: An Investigation of Statistical Cues to Word Boundaries
|
|
|
|
BASE
|
|
Show details
|
|
|
| 47 |
Processing continuous speech in infancy: From major prosodic units to isolated word forms
|
|
|
|
In: The Oxford Handbook of Developmental Linguistics ; https://hal-univ-bourgogne.archives-ouvertes.fr/hal-02934162 ; Edited by Jeffrey L. Lidz, William Snyder, and Joe Pater. The Oxford Handbook of Developmental Linguistics, Oxford University Press, pp.133-156, 2016, 9780199601264. ⟨10.1093/oxfordhb/9780199601264.013.8⟩ ; https://www.oxfordhandbooks.com/view/10.1093/oxfordhb/9780199601264.001.0001/oxfordhb-9780199601264 (2016)
|
|
BASE
|
|
Show details
|
|
|
| 48 |
Towards describing Tibetan syntax: From word segmentation to rewrite rules through a semi-automated workflow
|
|
|
|
In: Hildt, Hélios. (2016). Towards describing Tibetan syntax: From word segmentation to rewrite rules through a semi-automated workflow. Himalayan Linguistics, 15(1). doi:10.5070/H915129932. Retrieved from: http://www.escholarship.org/uc/item/3q29t25v (2016)
|
|
BASE
|
|
Show details
|
|
|
| 49 |
Unsupervised learning of morphology in the USSR
|
|
|
|
In: Journées internationales d'Analyse statistique des Données Textuelles ; https://hal.archives-ouvertes.fr/hal-01620908 ; Journées internationales d'Analyse statistique des Données Textuelles, Damon Mayaffre, Céline Poudat, Laurent Vanni, Véronique Magri, Peter Follette, Jun 2016, Nice, France (2016)
|
|
BASE
|
|
Show details
|
|
|
| 50 |
Automatic Handwritten Character Segmentation for Paleographical Character Shape Analysis
|
|
|
|
In: 2016 12th IAPR Workshop on Document Analysis Systems (DAS) ; https://hal.archives-ouvertes.fr/hal-02425715 ; 2016 12th IAPR Workshop on Document Analysis Systems (DAS), Apr 2016, Santorini, France. pp.42-47, ⟨10.1109/DAS.2016.74⟩ (2016)
|
|
BASE
|
|
Show details
|
|
|
| 51 |
The influence of F0 discontinuity on intonational cues to word segmentation: A preliminary investigation
|
|
|
|
In: Speech Prosody ; https://hal.archives-ouvertes.fr/hal-01452826 ; Speech Prosody, May 2016, Boston, United States ; http://sites.bu.edu/speechprosody2016/ (2016)
|
|
BASE
|
|
Show details
|
|
|
| 52 |
Isolated Words Selectively Enhance Memory for High Transitional Probability Sound Sequences
|
|
|
|
In: Masters Theses (2016)
|
|
BASE
|
|
Show details
|
|
|
| 53 |
British English infants segment words only with exaggerated infant-directed speech stimuli.
|
|
|
|
BASE
|
|
Show details
|
|
|
| 54 |
The Bidirectional Long-Short-Term Memory Neural Network based Word Retrieval for Arabic Documents
|
|
|
|
In: ISSN: 2054-7390 ; Transactions on Machine Learning and Artificial Intelligence ; https://hal.archives-ouvertes.fr/hal-03371886 ; Transactions on Machine Learning and Artificial Intelligence, Society for Science and Education, United Kingdom, 2015, 3 (1), pp.16-27. ⟨10.14738/tmlai.31.863⟩ ; https://journals.scholarpublishing.org/index.php/TMLAI/article/view/863 (2015)
|
|
BASE
|
|
Show details
|
|
|
| 56 |
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)
|
|
Abstract:
Conference of 13th International Conference on Document Analysis and Recognition, ICDAR 2015 ; Conference Date: 23 August 2015 Through 26 August 2015; Conference Code:118256 ; 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 words. In a previous work, dynamic dictionaries were built from Web resources and successfully applied to isolated word recognition. In the present work we extend this approach to text-line recognition. Line segmentation into words is needed to exploit dynamic dictionaries and it is performed using BLSTM classifiers to align filler models and word sequence outputs. Words are then classified based on the confidence score into anchor and non-anchor words (AWs and NAWs). AWs are equated to the BLSTM outputs and used as such. Dynamic dictionaries are built for NAWs by exploiting Web resources for their character sequence and for neighboring AWs. Text-lines are decoded again using dynamic dictionaries and re-estimated language model. We conduct experiments on the publicly available RIMES database and show that the introduction of the dynamic dictionary is beneficial. Equally important, we show that the gain increases as the proportion of OOVs increases.
|
|
Keyword:
[INFO]Computer Science [cs]; Character recognition; Computational linguistics; Confidence score; Dynamic dictionaries; Hand-written text recognition; Handwriting recognition; Isolated word recognition; Line segmentation; Out of vocabulary words; Speech recognition; Text-line recognition; World Wide Web
|
|
URL: https://hal-cea.archives-ouvertes.fr/cea-01841169
https://doi.org/10.1109/ICDAR.2015.7333805
|
|
BASE
|
|
Hide details
|
|
|
| 57 |
Quantas sílabas tem “cháv(e)na”? Sobre o impacto dos apagamentos vocálicos na segmentação silábica de crianças no ensino pré-escolar
|
|
|
|
In: Linguística : Revista de Estudos Linguísticos da Universidade do Porto, Vol 10, Pp 31-58 (2015) (2015)
|
|
BASE
|
|
Show details
|
|
|
| 58 |
Syntactic Parsing and Compound Recognition via Dual Decomposition: Application to French
|
|
|
|
In: COLING 2014, the 25th International Conference on Computational Linguistics ; https://hal.archives-ouvertes.fr/hal-01074298 ; COLING 2014, the 25th International Conference on Computational Linguistics, Aug 2014, Dublin, Ireland. pp.1875-1885 (2014)
|
|
BASE
|
|
Show details
|
|
|
| 59 |
Bridging the gap between speech technology and natural language processing: an evaluation toolbox for term discovery systems
|
|
|
|
In: Language Resources and Evaluation Conference ; https://hal.inria.fr/hal-01026368 ; Language Resources and Evaluation Conference, May 2014, Reykyavik, Iceland (2014)
|
|
BASE
|
|
Show details
|
|
|
| 60 |
Exploring issues in lexical acquisition using Bayesian modelling
|
|
|
|
BASE
|
|
Show details
|
|
|
|
|
