Siva Reddy

Mila > À propos de Mila > Équipe > Siva Reddy
Membre Académique Principal
Siva Reddy
Professeur adjoint, McGill University
Siva Reddy

Siva Reddy est professeur adjoint en informatique et linguistique à l’Université McGill. Ses travaux portent sur les algorithmes qui permettent aux ordinateurs de comprendre et traiter les langues humaines. Siva a fait ses études postdoctorales avec le Stanford NLP Group. Son expertise inclut la construction de symboliques linguistiques et induites et de modèles d’apprentissage profond pour le langage. 

Publications

2021-08

Post-hoc Interpretability for Neural NLP: A Survey
Andreas Madsen, Siva Reddy and Sarath Chandar
arXiv preprint arXiv:2108.04840
(2021-08-10)
arxiv.orgPDF
Minimax and Neyman-Pearson Meta-Learning for Outlier Languages
Edoardo Maria Ponti, Rahul Aralikatte, Disha Shrivastava, Siva Reddy and Anders Sogaard
StereoSet: Measuring stereotypical bias in pretrained language models
Moin Nadeem, Anna Bethke and Siva Reddy

2021-06

End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answering.
Devendra Singh Sachan, Siva Reddy, William L. Hamilton, Chris Dyer and Dani Yogatama
arXiv preprint arXiv:2106.05346
(2021-06-09)
dblp.uni-trier.dePDF

2021-05

Explicitly Modeling Syntax in Language Models with Incremental Parsing and a Dynamic Oracle.
Yikang Shen, Shawn Tan, Alessandro Sordoni, Siva Reddy and Aaron C. Courville
Understanding by Understanding Not: Modeling Negation in Language Models.
Arian Hosseini, Siva Reddy, Dzmitry Bahdanau, R. Devon Hjelm, Alessandro Sordoni and Aaron C. Courville

2021-04

Back-Training excels Self-Training at Unsupervised Domain Adaptation of Question Generation and Passage Retrieval.
Devang Kulshreshtha, Robert Belfer, Iulian Vlad Serban and Siva Reddy
arXiv preprint arXiv:2104.08801
(2021-04-18)
ui.adsabs.harvard.eduPDF

2020-11

Universal Dependencies 2.7
Daniel Zeman, Joakim Nivre, Mitchell Abrams, Elia Ackermann, Noëmi Aepli, Hamid Aghaei, Željko Agić, Amir Ahmadi, Lars Ahrenberg, Chika Kennedy Ajede, Gabrielė Aleksandravičiūtė, Ika Alfina, Lene Antonsen, Katya Aplonova, Angelina Aquino, Carolina Aragon, Maria Jesus Aranzabe, Þórunn Arnardóttir, Gashaw Arutie, Jessica Naraiswari Arwidarasti... (395 more)
(venue unknown)
(2020-11-15)
lindat.cz
MeDAL: Medical Abbreviation Disambiguation Dataset for Natural Language Understanding Pretraining
Zhi Wen, Xing Han Lu and Siva Reddy
Learning Improvised Chatbots from Adversarial Modifications of Natural Language Feedback
Makesh Narsimhan Sreedhar, Kun Ni and Siva Reddy

2020-10

Explicitly Modeling Syntax in Language Model improves Generalization.
Yikang Shen, Shawn Tan, Alessandro Sordoni, Siva Reddy and Aaron C. Courville
arXiv preprint arXiv:2011.07960
(2020-10-21)
ui.adsabs.harvard.eduPDF

2020-05

Universal Dependencies 2.6
Daniel Zeman, Joakim Nivre, Mitchell Abrams, Elia Ackermann, Noëmi Aepli, Željko Agić, Lars Ahrenberg, Chika Kennedy Ajede, Gabrielė Aleksandravičiūtė, Lene Antonsen, Katya Aplonova, Angelina Aquino, Maria Jesus Aranzabe, Gashaw Arutie, Masayuki Asahara, Luma Ateyah, Furkan Atmaca, Mohammed Attia, Aitziber Atutxa, Liesbeth Augustinus... (349 more)
(venue unknown)
(2020-05-15)
hdl.handle.net
Words aren’t enough, their order matters: on the robustness of grounding visual referring expressions
Arjun R. Akula, Spandana Gella, Yaser Al-Onaizan, Song-Chun Zhu and Siva Reddy

2020-01

You could have said that instead: Improving Chatbots with Natural Language Feedback.
Makesh Narsimhan Sreedhar, Kun Ni and Siva Reddy
EMNLP 2020
(2020-01-01)
www.aclweb.orgPDF

2019-11

Universal Dependencies 2.5
Daniel Zeman, Joakim Nivre, Mitchell Abrams, Noëmi Aepli, Željko Agić, Lars Ahrenberg, Gabrielė Aleksandravičiūtė, Lene Antonsen, Katya Aplonova, Maria Jesus Aranzabe, Gashaw Arutie, Masayuki Asahara, Luma Ateyah, Mohammed Attia, Aitziber Atutxa, Liesbeth Augustinus, Elena Badmaeva, Miguel Ballesteros, Esha Banerjee, Sebastian Bank... (324 more)
(venue unknown)
(2019-11-15)
hdl.handle.net

Publications collected and formatted using Paperoni

array(1) { ["wp-wpml_current_language"]=> string(2) "fr" }