Arvind Neelakantan

is this you? claim profile

∙ 0 followers
Google ∙ University of Massachusetts Amherst

Research Scientist at Google

On Task-Level Dialogue Composition of Generative Transformer Model

Task-oriented dialogue systems help users accomplish tasks such as booki...
10/09/2020 ∙ by Prasanna Parthasarathi, et al. ∙ 0 ∙ share

read it
Language Models are Few-Shot Learners

Recent work has demonstrated substantial gains on many NLP tasks and ben...
05/28/2020 ∙ by Tom B. Brown, et al. ∙ 33 ∙ share

read it
Trading Off Diversity and Quality in Natural Language Generation

For open-ended language generation tasks such as storytelling and dialog...
04/22/2020 ∙ by Hugh Zhang, et al. ∙ 0 ∙ share

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

Task-oriented dialog presents a difficult challenge encompassing multipl...
10/31/2019 ∙ by Arvind Neelakantan, et al. ∙ 0 ∙ share

read it
Taskmaster-1: Toward a Realistic and Diverse Dialog Dataset

A significant barrier to progress in data-driven approaches to building ...
09/01/2019 ∙ by Bill Byrne, et al. ∙ 0 ∙ share

read it
Parallel Scheduled Sampling

Auto-regressive models are widely used in sequence generation problems. ...
06/11/2019 ∙ by Daniel Duckworth, et al. ∙ 0 ∙ share

read it
Theory and Experiments on Vector Quantized Autoencoders

Deep neural networks with discrete latent variables offer the promise of...
05/28/2018 ∙ by Aurko Roy, et al. ∙ 0 ∙ share

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

We introduce RelNet: a new model for relational reasoning. RelNet is a m...
06/22/2017 ∙ by Trapit Bansal, et al. ∙ 0 ∙ share

read it
Learning a Natural Language Interface with Neural Programmer

Learning a natural language interface for database tables is a challengi...
11/28/2016 ∙ by Arvind Neelakantan, et al. ∙ 0 ∙ share

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

Our goal is to combine the rich multistep inference of symbolic logical ...
07/05/2016 ∙ by Rajarshi Das, et al. ∙ 0 ∙ share

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

Universal schema predicts the types of entities and relations in a knowl...
06/18/2016 ∙ by Patrick Verga, et al. ∙ 0 ∙ share

read it
Adding Gradient Noise Improves Learning for Very Deep Networks

Deep feedforward and recurrent networks have achieved impressive results...
11/21/2015 ∙ by Arvind Neelakantan, et al. ∙ 0 ∙ share

read it
Neural Programmer: Inducing Latent Programs with Gradient Descent

Deep neural networks have achieved impressive supervised classification ...
11/16/2015 ∙ by Arvind Neelakantan, et al. ∙ 0 ∙ share

read it
Compositional Vector Space Models for Knowledge Base Completion

Knowledge base (KB) completion adds new facts to a KB by making inferenc...
04/24/2015 ∙ by Arvind Neelakantan, et al. ∙ 0 ∙ share

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

Most of previous work in knowledge base (KB) completion has focused on t...
04/24/2015 ∙ by Arvind Neelakantan, et al. ∙ 0 ∙ share

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

There is rising interest in vector-space word embeddings and their use i...
04/24/2015 ∙ by Arvind Neelakantan, et al. ∙ 0 ∙ share

read it
Learning Dictionaries for Named Entity Recognition using Minimal Supervision

This paper describes an approach for automatic construction of dictionar...
04/24/2015 ∙ by Arvind Neelakantan, et al. ∙ 0 ∙ share

read it

Arvind Neelakantan

Featured Co-authors

Quoc V. Le

Andrew McCallum

Samy Bengio

Ilya Sutskever

Bill Byrne

Łukasz Kaiser

Michael Collins

Ming-Wei Chang

David Belanger

Xifeng Yan

Ashish Vaswani

On Task-Level Dialogue Composition of Generative Transformer Model

Language Models are Few-Shot Learners

Trading Off Diversity and Quality in Natural Language Generation

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

Taskmaster-1: Toward a Realistic and Diverse Dialog Dataset

Parallel Scheduled Sampling

Theory and Experiments on Vector Quantized Autoencoders

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

Learning a Natural Language Interface with Neural Programmer

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

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

Adding Gradient Noise Improves Learning for Very Deep Networks

Neural Programmer: Inducing Latent Programs with Gradient Descent

Compositional Vector Space Models for Knowledge Base Completion

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

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

Learning Dictionaries for Named Entity Recognition using Minimal Supervision