Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Arvind Neelakantan

On Task-Level Dialogue Composition of Generative Transformer Model


Oct 09, 2020
Prasanna Parthasarathi, Arvind Neelakantan, Sharan Narang

* 8 pages; Accepted at Workshop on Insights from Negative Results in NLP 

  Access Paper or Ask Questions

Language Models are Few-Shot Learners


Jun 05, 2020
Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel M. Ziegler, Jeffrey Wu, Clemens Winter, Christopher Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, Dario Amodei

* 40+32 pages 

  Access Paper or Ask Questions

Trading Off Diversity and Quality in Natural Language Generation


Apr 22, 2020
Hugh Zhang, Daniel Duckworth, Daphne Ippolito, Arvind Neelakantan


  Access Paper or Ask Questions

Neural Assistant: Joint Action Prediction, Response Generation, and Latent Knowledge Reasoning


Oct 31, 2019
Arvind Neelakantan, Semih Yavuz, Sharan Narang, Vishaal Prasad, Ben Goodrich, Daniel Duckworth, Chinnadhurai Sankar, Xifeng Yan


  Access Paper or Ask Questions

Taskmaster-1: Toward a Realistic and Diverse Dialog Dataset


Sep 01, 2019
Bill Byrne, Karthik Krishnamoorthi, Chinnadhurai Sankar, Arvind Neelakantan, Daniel Duckworth, Semih Yavuz, Ben Goodrich, Amit Dubey, Andy Cedilnik, Kyu-Young Kim

* To appear at EMNLP 2019 

  Access Paper or Ask Questions

Parallel Scheduled Sampling


Jun 11, 2019
Daniel Duckworth, Arvind Neelakantan, Ben Goodrich, Lukasz Kaiser, Samy Bengio

* Initial submission 

  Access Paper or Ask Questions

Theory and Experiments on Vector Quantized Autoencoders


Jul 20, 2018
Aurko Roy, Ashish Vaswani, Arvind Neelakantan, Niki Parmar


  Access Paper or Ask Questions

RelNet: End-to-End Modeling of Entities & Relations


Nov 16, 2017
Trapit Bansal, Arvind Neelakantan, Andrew McCallum

* Accepted in AKBC 2017 

  Access Paper or Ask Questions

Chains of Reasoning over Entities, Relations, and Text using Recurrent Neural Networks


May 01, 2017
Rajarshi Das, Arvind Neelakantan, David Belanger, Andrew McCallum

* accepted to EACL 2017 (fixed latex formatting in previous version) 

  Access Paper or Ask Questions

Learning a Natural Language Interface with Neural Programmer


Mar 02, 2017
Arvind Neelakantan, Quoc V. Le, Martin Abadi, Andrew McCallum, Dario Amodei

* Published as a conference paper at ICLR 2017 

  Access Paper or Ask Questions

Generalizing to Unseen Entities and Entity Pairs with Row-less Universal Schema


Jan 09, 2017
Patrick Verga, Arvind Neelakantan, Andrew McCallum

* EACL 2017. arXiv admin note: text overlap with arXiv:1604.06361 

  Access Paper or Ask Questions

Neural Programmer: Inducing Latent Programs with Gradient Descent


Aug 04, 2016
Arvind Neelakantan, Quoc V. Le, Ilya Sutskever

* Accepted as a conference paper at ICLR 2015 

  Access Paper or Ask Questions

Adding Gradient Noise Improves Learning for Very Deep Networks


Nov 21, 2015
Arvind Neelakantan, Luke Vilnis, Quoc V. Le, Ilya Sutskever, Lukasz Kaiser, Karol Kurach, James Martens


  Access Paper or Ask Questions

Compositional Vector Space Models for Knowledge Base Completion


May 27, 2015
Arvind Neelakantan, Benjamin Roth, Andrew McCallum

* The 53rd Annual Meeting of the Association for Computational Linguistics and The 7th International Joint Conference of the Asian Federation of Natural Language Processing, 2015 

  Access Paper or Ask Questions

Inferring Missing Entity Type Instances for Knowledge Base Completion: New Dataset and Methods


Apr 24, 2015
Arvind Neelakantan, Ming-Wei Chang

* North American Chapter of the Association for Computational Linguistics- Human Language Technologies, 2015 

  Access Paper or Ask Questions

Efficient Non-parametric Estimation of Multiple Embeddings per Word in Vector Space


Apr 24, 2015
Arvind Neelakantan, Jeevan Shankar, Alexandre Passos, Andrew McCallum

* In Conference on Empirical Methods in Natural Language Processing, 2014 

  Access Paper or Ask Questions

Learning Dictionaries for Named Entity Recognition using Minimal Supervision


Apr 24, 2015
Arvind Neelakantan, Michael Collins

* In 14th Conference of the European Chapter of the Association for Computational Linguistic, 2014 

  Access Paper or Ask Questions