1 |
Improving Machine Translation of Arabic Dialects through Multi-Task Learning
|
|
|
|
In: 20th International Conference Italian Association for Artificial Intelligence:AIxIA 2021 ; https://hal.archives-ouvertes.fr/hal-03435996 ; 20th International Conference Italian Association for Artificial Intelligence:AIxIA 2021, Dec 2021, MILAN/Virtual, Italy (2021)
|
|
BASE
|
|
Show details
|
|
2 |
Improving Machine Translation of Arabic Dialects through Multi-Task Learning ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
SimSCL: A Simple fully-Supervised Contrastive Learning Framework for Text Representation
|
|
|
|
In: AJCAI 2021 - 34th Australasian Joint Conference on Artificial Intelligence ; https://hal.archives-ouvertes.fr/hal-03367972 ; AJCAI 2021 - 34th Australasian Joint Conference on Artificial Intelligence, Feb 2022, Sydney, Australia (1479)
|
|
Abstract:
International audience ; During the last few years, deep supervised learning models have been shown to achieve state-of-the-art results for Natural Language Processing tasks. Most of these models are trained by minimizing the commonly used cross-entropy loss. However, the latter may suffer from several shortcomings such as sub-optimal generalization and unstable fine-tuning. Inspired by the recent works on self-supervised contrastive representation learning, we present SimSCL, a framework for binary text classification task that relies on two simple concepts: (i) Sampling positive and negative examples given an anchor by considering that sentences belonging to the same class as the anchor as positive examples and samples belonging to a different class as negative examples and (ii) Using a novel fully-supervised contrastive loss that enforces more compact clustering by leveraging label information more effectively. The experimental results show that our framework outperforms the standard cross-entropy loss in several benchmark datasets. Further experiments on Moroccan and Algerian dialects demonstrate that our framework also works well for under-resource languages.
|
|
Keyword:
[INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]; Contrastive Learning; Natural Language Processing; Neural Network; Supervised Learning
|
|
URL: https://hal.archives-ouvertes.fr/hal-03367972/file/Springer_Lecture_Notes_in_Computer_Science__3_.pdf https://hal.archives-ouvertes.fr/hal-03367972/document https://hal.archives-ouvertes.fr/hal-03367972
|
|
BASE
|
|
Hide details
|
|
|
|