TY - GEN
T1 - Text Transformations in Contrastive Self-Supervised Learning
T2 - 31st International Joint Conference on Artificial Intelligence, IJCAI 2022
AU - Bhattacharjee, Amrita
AU - Karami, Mansooreh
AU - Liu, Huan
N1 - Funding Information:
This research is supported by the DARPA (HR001120C0123) and ONR (N00014-21-1-4002). The views, opinions and/or findings expressed are those of the authors and should not be interpreted as representing the official views or policies of the Department of Defense or the U.S. Government.
Publisher Copyright:
© 2022 International Joint Conferences on Artificial Intelligence. All rights reserved.
PY - 2022
Y1 - 2022
N2 - Contrastive self-supervised learning has become a prominent technique in representation learning. The main step in these methods is to contrast semantically similar and dissimilar pairs of samples. However, in the domain of Natural Language Processing (NLP), the augmentation methods used in creating similar pairs with regard to contrastive learning (CL) assumptions are challenging. This is because, even simply modifying a word in the input might change the semantic meaning of the sentence, and hence, would violate the distributional hypothesis. In this review paper, we formalize the contrastive learning framework, emphasize the considerations that need to be addressed in the data transformation step, and review the state-of-the-art methods and evaluations for contrastive representation learning in NLP. Finally, we describe some challenges and potential directions for learning better text representations using contrastive methods.
AB - Contrastive self-supervised learning has become a prominent technique in representation learning. The main step in these methods is to contrast semantically similar and dissimilar pairs of samples. However, in the domain of Natural Language Processing (NLP), the augmentation methods used in creating similar pairs with regard to contrastive learning (CL) assumptions are challenging. This is because, even simply modifying a word in the input might change the semantic meaning of the sentence, and hence, would violate the distributional hypothesis. In this review paper, we formalize the contrastive learning framework, emphasize the considerations that need to be addressed in the data transformation step, and review the state-of-the-art methods and evaluations for contrastive representation learning in NLP. Finally, we describe some challenges and potential directions for learning better text representations using contrastive methods.
UR - http://www.scopus.com/inward/record.url?scp=85137893839&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85137893839&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85137893839
T3 - IJCAI International Joint Conference on Artificial Intelligence
SP - 5394
EP - 5401
BT - Proceedings of the 31st International Joint Conference on Artificial Intelligence, IJCAI 2022
A2 - De Raedt, Luc
A2 - De Raedt, Luc
PB - International Joint Conferences on Artificial Intelligence
Y2 - 23 July 2022 through 29 July 2022
ER -