21 |
Universal Dependencies 2.2
|
|
|
|
In: https://hal.archives-ouvertes.fr/hal-01930733 ; 2018 (2018)
|
|
BASE
|
|
Show details
|
|
24 |
Beyond task success: A closer look at jointly learning to see, ask, and GuessWhat ...
|
|
|
|
BASE
|
|
Show details
|
|
25 |
Distant Supervision from Disparate Sources for Low-Resource Part-of-Speech Tagging ...
|
|
|
|
BASE
|
|
Show details
|
|
26 |
The Best of Both Worlds: Lexical Resources To Improve Low-Resource Part-of-Speech Tagging ...
|
|
|
|
BASE
|
|
Show details
|
|
27 |
Bleaching Text: Abstract Features for Cross-lingual Gender Prediction ...
|
|
|
|
BASE
|
|
Show details
|
|
28 |
Universal Dependencies 2.1
|
|
|
|
In: https://hal.inria.fr/hal-01682188 ; 2017 (2017)
|
|
BASE
|
|
Show details
|
|
29 |
When is multitask learning effective? Semantic sequence prediction under varying data conditions
|
|
|
|
In: EACL 2017 - 15th Conference of the European Chapter of the Association for Computational Linguistics ; https://hal.inria.fr/hal-01677427 ; EACL 2017 - 15th Conference of the European Chapter of the Association for Computational Linguistics, Apr 2017, Valencia, Spain. pp.1-10 ; http://eacl2017.org/ (2017)
|
|
Abstract:
International audience ; Multitask learning has been applied successfully to a range of tasks, mostly mor-phosyntactic. However, little is known on when MTL works and whether there are data characteristics that help to determine its success. In this paper we evaluate a range of semantic sequence labeling tasks in a MTL setup. We examine different auxiliary tasks, amongst which a novel setup, and correlate their impact to data-dependent conditions. Our results show that MTL is not always effective, significant improvements are obtained only for 1 out of 5 tasks. When successful, auxiliary tasks with compact and more uniform label distributions are preferable.
|
|
Keyword:
[INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]
|
|
URL: https://hal.inria.fr/hal-01677427/file/eacl2017.pdf https://hal.inria.fr/hal-01677427 https://hal.inria.fr/hal-01677427/document
|
|
BASE
|
|
Hide details
|
|
30 |
Parsing Universal Dependencies without training
|
|
|
|
In: Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, ; EACL 2017 - 15th Conference of the European Chapter of the Association for Computational Linguistics ; https://hal.inria.fr/hal-01677405 ; EACL 2017 - 15th Conference of the European Chapter of the Association for Computational Linguistics, Apr 2017, Valencia, Spain. pp.229 - 239 ; http://eacl2017.org/ (2017)
|
|
BASE
|
|
Show details
|
|
33 |
Universal Dependencies 2.0 – CoNLL 2017 Shared Task Development and Test Data
|
|
|
|
BASE
|
|
Show details
|
|
35 |
ALL-IN-1: Short Text Classification with One Model for All Languages ...
|
|
|
|
BASE
|
|
Show details
|
|
37 |
Multilingual Projection for Parsing Truly Low-Resource Languageš
|
|
|
|
In: EISSN: 2307-387X ; Transactions of the Association for Computational Linguistics ; https://hal.inria.fr/hal-01426754 ; Transactions of the Association for Computational Linguistics, The MIT Press, 2016 (2016)
|
|
BASE
|
|
Show details
|
|
38 |
Supersense tagging with inter-annotator disagreement
|
|
|
|
In: Linguistic Annotation Workshop 2016 ; https://hal.inria.fr/hal-01426747 ; Linguistic Annotation Workshop 2016, Aug 2016, Berlin, Germany. pp.43 - 48 (2016)
|
|
BASE
|
|
Show details
|
|
|
|