Sökning: id:"swepub:oai:gup.ub.gu.se/291265" >
When is Multi-task ...
When is Multi-task Learning Beneficial for Low-Resource Noisy Code-switched User-generated Algerian Texts?
-
- Adouane, Wafia, 1985 (författare)
- Gothenburg University,Göteborgs universitet,Institutionen för filosofi, lingvistik och vetenskapsteori,Department of Philosophy, Linguistics and Theory of Science
-
- Bernardy, Jean-Philippe, 1978 (författare)
- Gothenburg University,Göteborgs universitet,Institutionen för filosofi, lingvistik och vetenskapsteori,Department of Philosophy, Linguistics and Theory of Science
-
(creator_code:org_t)
- Paris : European Language Resources Association, 2020
- 2020
- Engelska.
-
Ingår i: Fourth Workshop on Computational Approaches to Linguistic Code-Switching. Language Resources and Evaluation Conference (LREC 2020), Marseille, 11–16 May 202. - Paris : European Language Resources Association. - 9791095546665
- Relaterad länk:
-
https://gup.ub.gu.se...
Abstract
Ämnesord
Stäng
- We investigate when is it beneficial to simultaneously learn representations for several tasks, in low-resource settings. For this, we work with noisy user-generated texts in Algerian, a low-resource non-standardised Arabic variety. That is, to mitigate the problem of the data scarcity, we experiment with jointly learning progressively 4 tasks, namely code-switch detection, named entity recognition, spell normalisation and correction, and identifying users’ sentiments. The selection of these tasks is motivated by the lack of labelled data for automatic morpho-syntactic or semantic sequence-tagging tasks for Algerian, in contrast to the case of much multi-task learning for NLP. Our empirical results show that multi-task learning is beneficial for some tasks in particular settings, and that the effect of each task on another, the order of the tasks, and the size of the training data of the task with more data do matter. Moreover, the data augmentation that we performed with no external resources has been shown to be beneficial for certain tasks.
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap -- Språkteknologi (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Language Technology (hsv//eng)
Nyckelord
- Algerian Arabic
- code-switched user-generated data
- multi-task learning
- low-resource colloquial languages
Publikations- och innehållstyp
- ref (ämneskategori)
- kon (ämneskategori)
Hitta via bibliotek
Till lärosätets databas