Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Darvish, Kasra"'
We re-examine the situation entity (SE) classification task with varying amounts of available training data. We exploit a Transformer-based variational autoencoder to encode sentences into a lower dimensional latent space, which is used to generate t
Externí odkaz:
http://arxiv.org/abs/2109.07434
Autor:
Nguyen, Andre T., Richards, Luke E., Kebe, Gaoussou Youssouf, Raff, Edward, Darvish, Kasra, Ferraro, Frank, Matuszek, Cynthia
We propose a cross-modality manifold alignment procedure that leverages triplet loss to jointly learn consistent, multi-modal embeddings of language-based concepts of real-world items. Our approach learns these embeddings by sampling triples of ancho
Externí odkaz:
http://arxiv.org/abs/2009.05147
Autor:
Jenkins, Patrick, Sachdeva, Rishabh, Kebe, Gaoussou Youssouf, Higgins, Padraig, Darvish, Kasra, Raff, Edward, Engel, Don, Winder, John, Ferraro, Francis, Matuszek, Cynthia
Grounded language acquisition -- learning how language-based interactions refer to the world around them -- is amajor area of research in robotics, NLP, and HCI. In practice the data used for learning consists almost entirely of textual descriptions,
Externí odkaz:
http://arxiv.org/abs/2007.14987