b'Phil Blunsom'

research

∙ 07/31/2023

Structural Transfer Learning in NL-to-Bash Semantic Parsers

Large-scale pre-training has made progress in many fields of natural lan...

0 Kyle Duffy, et al. ∙

research

∙ 06/05/2023

On "Scientific Debt" in NLP: A Case for More Rigour in Language Model Pre-Training Research

This evidence-based position paper critiques current research practices ...

0 Made Nindyatama Nityasya, et al. ∙

research

∙ 05/30/2023

Intriguing Properties of Quantization at Scale

Emergent properties have been widely adopted as a term to describe behav...

10 Arash Ahmadian, et al. ∙

research

∙ 11/22/2022

Simplicity Bias in Transformers and their Ability to Learn Sparse Boolean Functions

Despite the widespread success of Transformers on NLP tasks, recent work...

0 Satwik Bhattamishra, et al. ∙

research

∙ 10/21/2022

Augmenting Multi-Turn Text-to-SQL Datasets with Self-Play

The task of context-dependent text-to-SQL aims to convert multi-turn use...

0 Qi Liu, et al. ∙

research

∙ 05/24/2022

Rethinking Evaluation Practices in Visual Question Answering: A Case Study on Out-of-Distribution Generalization

Vision-and-language (V L) models pretrained on large-scale multimodal ...

3 Aishwarya Agrawal, et al. ∙

research

∙ 05/23/2022

StreamingQA: A Benchmark for Adaptation to New Knowledge over Time in Question Answering Models

Knowledge and language understanding of models evaluated through questio...

0 Adam Liska, et al. ∙

research

∙ 03/14/2022

Revisiting the Compositional Generalization Abilities of Neural Sequence Models

Compositional generalization is a fundamental trait in humans, allowing ...

0 Arkil Patel, et al. ∙

research

∙ 03/01/2022

Transformer Grammars: Augmenting Transformer Language Models with Syntactic Inductive Biases at Scale

Transformer language models that are trained on vast amounts of data hav...

0 Laurent Sartran, et al. ∙

research

∙ 01/24/2022

Relational Memory Augmented Language Models

We present a memory-augmented approach to condition an autoregressive la...

1 Qi Liu, et al. ∙

research

∙ 10/31/2021

A Systematic Investigation of Commonsense Understanding in Large Language Models

Large language models have shown impressive performance on many natural ...

0 Xiang Lorraine Li, et al. ∙

research

∙ 03/18/2021

Pretraining the Noisy Channel Model for Task-Oriented Dialogue

Direct decoding for task-oriented dialogue is known to suffer from the e...

6 Qi Liu, et al. ∙

research

∙ 02/03/2021

Pitfalls of Static Language Modelling

Our world is open-ended, non-stationary and constantly evolving; thus wh...

0 Angeliki Lazaridou, et al. ∙

research

∙ 12/01/2020

Mutual Information Constraints for Monte-Carlo Objectives

A common failure mode of density models trained as variational autoencod...

0 Gábor Melis, et al. ∙

research

∙ 09/23/2020

The Struggles of Feature-Based Explanations: Shapley Values vs. Minimal Sufficient Subsets

For neural models to garner widespread public trust and ensure fairness,...

0 Oana-Maria Camburu, et al. ∙

research

∙ 05/27/2020

Syntactic Structure Distillation Pretraining For Bidirectional Encoders

Textual representation learners trained on large amounts of data have ac...

0 Adhiguna Kuncoro, et al. ∙

research

∙ 05/07/2020

Learning to Segment Actions from Observation and Narration

We apply a generative segmental model of task structure, guided by narra...

4 Daniel Fried, et al. ∙

research

∙ 03/16/2020

A Survey on Contextual Embeddings

Contextual embeddings, such as ELMo and BERT, move beyond global word re...

38 Qi Liu, et al. ∙

research

∙ 03/11/2020

Visual Grounding in Video for Unsupervised Word Translation

There are thousands of actively spoken languages on Earth, but a single ...

8 Gunnar A. Sigurdsson, et al. ∙

research

∙ 01/29/2020

Learning Robust and Multilingual Speech Representations

Unsupervised speech representation learning has shown remarkable success...

0 Kazuya Kawakami, et al. ∙

research

∙ 10/01/2019

Putting Machine Translation in Context with the Noisy Channel Model

We show that Bayes' rule provides a compelling mechanism for controlling...

0 Lei Yu, et al. ∙

research

∙ 09/20/2019

A Critical Analysis of Biased Parsers in Unsupervised Parsing

A series of recent papers has used a parsing algorithm due to Shen et al...

0 Chris Dyer, et al. ∙

research

∙ 09/04/2019

Mogrifier LSTM

Many advances in Natural Language Processing have been based upon more e...

0 Gábor Melis, et al. ∙

research

∙ 08/21/2019

WikiCREM: A Large Unsupervised Corpus for Coreference Resolution

Pronoun resolution is a major area of natural language understanding. Ho...

0 Vid Kocijan, et al. ∙

research

∙ 06/14/2019

Scalable Syntax-Aware Language Models Using Knowledge Distillation

Prior work has shown that, on small amounts of training data, syntactic ...

0 Adhiguna Kuncoro, et al. ∙

research

∙ 01/31/2019

Learning and Evaluating General Linguistic Intelligence

We define general linguistic intelligence as the ability to reuse previo...

8 Dani Yogatama, et al. ∙

research

∙ 12/04/2018

e-SNLI: Natural Language Inference with Natural Language Explanations

In order for machine learning to garner widespread public adoption, mode...

0 Oana-Maria Camburu, et al. ∙

research

∙ 12/04/2018

e-SNLI: Natural Language Inference withNatural Language Explanations

In order for machine learning to garner widespread public adoption, mode...

0 Oana-Maria Camburu, et al. ∙

research

∙ 11/27/2018

Learning with Stochastic Guidance for Navigation

Due to the sparse rewards and high degree of environment variation, rein...

0 Linhai Xie, et al. ∙

research

∙ 11/26/2018

Sentence Encoding with Tree-constrained Relation Networks

The meaning of a sentence is a function of the relations that hold betwe...

0 Lei Yu, et al. ∙

research

∙ 11/23/2018

Unsupervised Word Discovery with Segmental Neural Language Models

We propose a segmental neural language model that combines the represent...

0 Kazuya Kawakami, et al. ∙

research

∙ 10/04/2018

Transferring Physical Motion Between Domains for Neural Inertial Tracking

Inertial information processing plays a pivotal role in ego-motion aware...

0 Changhao Chen, et al. ∙

research

∙ 08/01/2018

Neural Arithmetic Logic Units

Neural networks can learn to represent and manipulate numerical informat...

6 Andrew Trask, et al. ∙

research

∙ 07/04/2018

Encoding Spatial Relations from Natural Language

Natural language processing has made significant inroads into learning t...

2 Tiago Ramalho, et al. ∙

research

∙ 05/23/2018

Pushing the bounds of dropout

We show that dropout training is best understood as performing MAP estim...

0 Gábor Melis, et al. ∙

research

∙ 12/19/2017

The NarrativeQA Reading Comprehension Challenge

Reading comprehension (RC)---in contrast to information retrieval---requ...

0 Tomáš Kočiský, et al. ∙

research

∙ 10/26/2017

Understanding Grounded Language Learning Agents

Neural network-based systems can now learn to locate the referents of wo...

0 Felix Hill, et al. ∙

research

∙ 07/18/2017

On the State of the Art of Evaluation in Neural Language Models

Ongoing innovations in recurrent neural network architectures have provi...

0 Gábor Melis, et al. ∙

research

∙ 06/20/2017

Grounded Language Learning in a Simulated 3D World

We are increasingly surrounded by artificially intelligent technology th...

0 Karl Moritz Hermann, et al. ∙

research

∙ 06/01/2017

Discovering Discrete Latent Topics with Neural Variational Inference

Topic models have been widely explored as probabilistic generative model...

0 Yishu Miao, et al. ∙

research

∙ 05/29/2017

Latent Intention Dialogue Models

Developing a dialogue agent that is capable of making autonomous decisio...

0 Tsung-Hsien Wen, et al. ∙

research

∙ 05/11/2017

Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems

Solving algebraic word problems requires executing a series of arithmeti...

0 Wang Ling, et al. ∙

research

∙ 04/24/2017

Robust Incremental Neural Semantic Graph Parsing

Parsing sentences to linguistically-expressive semantic representations ...

0 Jan Buys, et al. ∙

research

∙ 04/23/2017

Learning to Create and Reuse Words in Open-Vocabulary Neural Language Modeling

Fixed-vocabulary language models fail to account for one of the most cha...

0 Kazuya Kawakami, et al. ∙

research

∙ 03/06/2017

Generative and Discriminative Text Classification with Recurrent Neural Networks

We empirically characterize the performance of discriminative and genera...

0 Dani Yogatama, et al. ∙

research

∙ 11/28/2016

Learning to Compose Words into Sentences with Reinforcement Learning

We use reinforcement learning to learn tree-structured neural networks f...

0 Dani Yogatama, et al. ∙

research

∙ 11/08/2016

The Neural Noisy Channel

We formulate sequence to sequence transduction as a noisy channel decodi...

0 Lei Yu, et al. ∙

research

∙ 11/05/2016

Reference-Aware Language Models

We propose a general class of language models that treat reference as an...

0 Zichao Yang, et al. ∙

research

∙ 09/29/2016

Semantic Parsing with Semi-Supervised Sequential Autoencoders

We present a novel semi-supervised approach for sequence transduction an...

0 Tomáš Kočiský, et al. ∙

research

∙ 09/26/2016

Online Segment to Segment Neural Transduction

We introduce an online neural sequence to sequence model that learns to ...

0 Lei Yu, et al. ∙

Phil Blunsom

Featured Co-authors