Zobrazeno 1 - 10
of 12
pro vyhledávání: '"Kanagal, Bhargav"'
Large language models have ushered in a golden age of semantic parsing. The seq2seq paradigm allows for open-schema and abstractive attribute and relation extraction given only small amounts of finetuning data. Language model pretraining has simultan
Externí odkaz:
http://arxiv.org/abs/2212.10770
Autor:
Yang, Li, Wang, Qifan, Yu, Zac, Kulkarni, Anand, Sanghai, Sumit, Shu, Bin, Elsas, Jon, Kanagal, Bhargav
Attribute value extraction refers to the task of identifying values of an attribute of interest from product information. Product attribute values are essential in many e-commerce scenarios, such as customer service robots, product ranking, retrieval
Externí odkaz:
http://arxiv.org/abs/2112.08663
Autor:
Manku, Gurmeet, Lee-Thorp, James, Kanagal, Bhargav, Ainslie, Joshua, Feng, Jingchen, Pearson, Zach, Anjorin, Ebenezer, Gandhe, Sudeep, Eckstein, Ilya, Rosswog, Jim, Sanghai, Sumit, Pohl, Michael, Adams, Larry, Sivakumar, D.
We present ShopTalk, a multi-turn conversational faceted search system for shopping that is designed to handle large and complex schemas that are beyond the scope of state of the art slot-filling systems. ShopTalk decouples dialog management from ful
Externí odkaz:
http://arxiv.org/abs/2109.00702
Autor:
Zemlyanskiy, Yury, Gandhe, Sudeep, He, Ruining, Kanagal, Bhargav, Ravula, Anirudh, Gottweis, Juraj, Sha, Fei, Eckstein, Ilya
This paper explores learning rich self-supervised entity representations from large amounts of the associated text. Once pre-trained, these models become applicable to multiple entity-centric tasks such as ranked retrieval, knowledge base completion,
Externí odkaz:
http://arxiv.org/abs/2102.13247
Transformer is the backbone of modern NLP models. In this paper, we propose RealFormer, a simple and generic technique to create Residual Attention Layer Transformer networks that significantly outperform the canonical Transformer and its variants (B
Externí odkaz:
http://arxiv.org/abs/2012.11747
In recent years, interest in recommender research has shifted from explicit feedback towards implicit feedback data. A diversity of complex models has been proposed for a wide variety of applications. Despite this, learning from implicit feedback is
Externí odkaz:
http://arxiv.org/abs/1611.04666
Autor:
Kanagal, Bhargav, Ahmed, Amr, Pandey, Sandeep, Josifovski, Vanja, Yuan, Jeff, Garcia-Pueyo, Lluis
Publikováno v:
Proceedings of the VLDB Endowment (PVLDB), Vol. 5, No. 10, pp. 956-967 (2012)
Recommender systems based on latent factor models have been effectively used for understanding user interests and predicting future actions. Such models work by projecting the users and items into a smaller dimensional space, thereby clustering simil
Externí odkaz:
http://arxiv.org/abs/1207.0136
Autor:
Ahmed, Amr, Kanagal, Bhargav, Pandey, Sandeep, Josifovski, Vanja, Pueyo, Lluis Garcia, Yuan, Jeff
Publikováno v:
Proceedings of the Sixth ACM International Conference Web Search & Data Mining; 2/4/2013, p385-394, 10p
Autor:
Kanagal, Bhargav, Ahmed, Amr, Pandey, Sandeep, Josifovski, Vanja, Garcia-Pueyo, Lluis, Yuan, Jeff
Publikováno v:
2013 IEEE 29th International Conference on Data Engineering (ICDE); 2013, p386-397, 12p
Publikováno v:
Proceedings of the 2011 International Conference: Management of Data; 6/12/2011, p841-852, 12p