Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Myeongho Jeong"'
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 36:10526-10534
Despite the super-human accuracy of recent deep models in NLP tasks, their robustness is reportedly limited due to their reliance on spurious patterns. We thus aim to leverage contrastive learning and counterfactual augmentation for robustness. For a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4208eb3308f4e764261b93c3eb85a6c6
https://doi.org/10.1609/aaai.v36i10.21296
https://doi.org/10.1609/aaai.v36i10.21296
Publikováno v:
IEEE/ACM Transactions on Audio, Speech, and Language Processing. 29:2541-2550
This paper studies the dialogue response selection task. As state-of-the-arts are neural models requiring a large training set, data augmentation has been considered as a means to overcome the sparsity of observational annotation, where only one obse
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c716c8e92fe36c37c1129f41259942af
https://doi.org/10.1109/taslp.2021.3076876
https://doi.org/10.1109/taslp.2021.3076876
Publikováno v:
CIKM
Classification datasets are often biased in observations, leaving onlya few observations for minority classes. Our key contribution is de-tecting and reducing Under-represented (U-) and Over-represented(O-) artifacts from dataset imbalance, by propos
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f98112b982a314817eaecd8281b76667
https://doi.org/10.1145/3459637.3482077
https://doi.org/10.1145/3459637.3482077
Publikováno v:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7d2fcbead88346acf02d545e5cb21732
https://doi.org/10.18653/v1/2021.emnlp-main.209
https://doi.org/10.18653/v1/2021.emnlp-main.209
Publikováno v:
INTERSPEECH
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0c80537c6a5702aaa9da7b803f9ec20f
https://doi.org/10.21437/interspeech.2020-1968
https://doi.org/10.21437/interspeech.2020-1968
Publikováno v:
Proceedings of SustaiNLP: Workshop on Simple and Efficient Natural Language Processing.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::94e38b861d53612f6830a9c15fc1c678
https://doi.org/10.18653/v1/2020.sustainlp-1.22
https://doi.org/10.18653/v1/2020.sustainlp-1.22