Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Teru, Komal K."'
Autor:
Teru, Komal K.
Publikováno v:
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, 2023, 1112--1124
Due to the semantic complexity of the Relation extraction (RE) task, obtaining high-quality human labelled data is an expensive and noisy process. To improve the sample efficiency of the models, semi-supervised learning (SSL) methods aim to leverage
Externí odkaz:
http://arxiv.org/abs/2306.10153
Autor:
Teru, Komal K., Chakraborty, Aishik
Societal bias towards certain communities is a big problem that affects a lot of machine learning systems. This work aims at addressing the racial bias present in many modern gender recognition systems. We learn race invariant representations of huma
Externí odkaz:
http://arxiv.org/abs/1911.08556
Off-policy deep reinforcement learning (RL) algorithms are incapable of learning solely from batch offline data without online interactions with the environment, due to the phenomenon known as \textit{extrapolation error}. This is often due to past d
Externí odkaz:
http://arxiv.org/abs/1911.06970
The dominant paradigm for relation prediction in knowledge graphs involves learning and operating on latent representations (i.e., embeddings) of entities and relations. However, these embedding-based methods do not explicitly capture the composition
Externí odkaz:
http://arxiv.org/abs/1911.06962