Page: 1... 4 5 6 7 8 9 10 11 12... 82
141 |
Desenvolvimento e validação do instrumento de compreensão de expressões idiomáticas ; Idioms comprehension instrument : development and validation
|
|
|
|
BASE
|
|
Show details
|
|
142 |
The teaching, learning and testing of te reo Māori in tertiary institutions in Aotearoa/New Zealand
|
|
|
|
BASE
|
|
Show details
|
|
143 |
Science literacy in Saudi Arabia through language analysis of a secondary school physics textbook
|
|
|
|
BASE
|
|
Show details
|
|
144 |
Designing and assessing a digital, discipline-specific literacy assessment tool
|
|
|
|
BASE
|
|
Show details
|
|
145 |
Contextualized bilingualism among adolescents from four different ethnic groups in Indonesia
|
|
|
|
BASE
|
|
Show details
|
|
147 |
Test-takers’ contribution to the validation of uses of high-stakes language tests
|
|
|
|
BASE
|
|
Show details
|
|
148 |
The Acquisition Path of [w]-final Plurals in Brazilian Portuguese
|
|
|
|
In: Journal of Portuguese Linguistics, Vol 17, Iss 1 (2018) (2018)
|
|
BASE
|
|
Show details
|
|
149 |
A Comparative Analysis of the Apology Strategy between Turkish EFL Learners and English Native Speakers
|
|
|
|
In: Applied Linguistics Research Journal, Vol 2, Iss 3, Pp 48-57 (2018) (2018)
|
|
BASE
|
|
Show details
|
|
150 |
Washback of English national exams at ninth-grade level in Thailand and Indonesia
|
|
|
|
In: Indonesian Journal of Applied Linguistics, Vol 8, Iss 1, Pp 167-176 (2018) (2018)
|
|
BASE
|
|
Show details
|
|
151 |
THE PROFILE OF EFL LEARNERS AS MEASURED BY AN ENGLISH PROFICIENCY TEST
|
|
|
|
In: JEELS (Journal of English Education and Linguistics Studies), Vol 5, Iss 1, Pp 115-145 (2018) (2018)
|
|
BASE
|
|
Show details
|
|
152 |
The Acquisition Path of [w]-final Plurals in Brazilian Portuguese
|
|
|
|
In: Journal of Portuguese Linguistics, Vol 17, Iss 1 (2018) (2018)
|
|
BASE
|
|
Show details
|
|
153 |
A Cross-Sectional Study on Vocabulary Size Among Different Levels of the University Students
|
|
|
|
In: ELT Worldwide: Journal of English Language Teaching, Vol 5, Iss 1, Pp 64-72 (2018) (2018)
|
|
BASE
|
|
Show details
|
|
154 |
Language Assimilation and Performance in Achievement Tests among Immigrant Children: Evidence from a Field Experiment
|
|
|
|
BASE
|
|
Show details
|
|
155 |
Teacher Beliefs And Practices For An English Language Achievement Test
|
|
|
|
In: Ikala: Revista de Lenguaje y Cultura, Vol 23, Iss 1, Pp 25-44 (2018) (2018)
|
|
BASE
|
|
Show details
|
|
156 |
Diagnostic study on teachers’ beliefs and practices in foreign language assessment
|
|
|
|
In: Ikala: Revista de Lenguaje y Cultura, Vol 23, Iss 1 (2018) (2018)
|
|
BASE
|
|
Show details
|
|
157 |
Desenvolvimento e validação do instrumento de compreensão de expressões idiomáticas
|
|
|
|
In: Revista de Estudos da Linguagem, Vol 26, Iss 2, Pp 571-591 (2018) (2018)
|
|
BASE
|
|
Show details
|
|
158 |
A common neural hub resolves syntactic and non-syntactic conflict through cooperation with task-specific networks.
|
|
|
|
BASE
|
|
Show details
|
|
159 |
The C-Test: A Valid Measure to Test Second Language Proficiency?
|
|
|
|
In: https://hal-hprints.archives-ouvertes.fr/hprints-01491274 ; 2017 (2017)
|
|
BASE
|
|
Show details
|
|
160 |
Strategies to select examples for Active Learning with Conditional Random Fields
|
|
|
|
In: CICLing 2017 - 18th International Conference on Computational Linguistics and Intelligent Text Processing ; https://hal.archives-ouvertes.fr/hal-01621338 ; CICLing 2017 - 18th International Conference on Computational Linguistics and Intelligent Text Processing, Apr 2017, Budapest, Hungary. pp.1-14 (2017)
|
|
Abstract:
International audience ; Nowadays, many NLP problems are tackled as supervised machine learning tasks. Consequently, the cost of the expertise needed to annotate the examples is a widespread issue. Active learning offers a framework to that issue, allowing to control the annotation cost while maximizing the classifier performance, but it relies on the key step of choosing which example will be proposed to the expert. In this paper, we examine and propose such selection strategies in the specific case of Conditional Random Fields (CRF) which are largely used in NLP. On the one hand, we propose a simple method to correct a bias of some state-of-the-art selection techniques. On the other hand, we detail an original approach to select the examples, based on the respect of proportions in the datasets. These contributions are validated over a large range of experiments implying several datasets and tasks, including named entity recognition, chunking, phonetization, word sense disambiguation.
|
|
Keyword:
[INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]; [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]; active learning; conditional random fields; CRF; semi- supervised learning; statistical test of proportion
|
|
URL: https://hal.archives-ouvertes.fr/hal-01621338/file/Claveau_CICling2017.pdf https://hal.archives-ouvertes.fr/hal-01621338/document https://hal.archives-ouvertes.fr/hal-01621338
|
|
BASE
|
|
Hide details
|
|
Page: 1... 4 5 6 7 8 9 10 11 12... 82
|
|