Graham Neubig

Publications
Influence

XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization

J. Hu, Sebastian Ruder, Aditya Siddhant, Graham Neubig, Orhan Firat, M. Johnson
Computer Science
ICML
24 March 2020

We introduce the Cross-lingual TRansfer Evaluation of Multilingual Encoders XTREME benchmark, a multi-task benchmark for evaluating the cross- lingual generalization capabilities of multilingual representations across 40 languages and 9 tasks. Expand

Are Sixteen Heads Really Better than One?

Paul Michel, Omer Levy, Graham Neubig
Computer Science
NeurIPS
1 May 2019

We make the surprising observation that even if models have been trained using multiple heads, in practice, a large percentage of attention heads can be removed at test time without significantly impacting performance. Expand

Lagging Inference Networks and Posterior Collapse in Variational Autoencoders

Junxian He, Daniel Spokoyny, Graham Neubig, Taylor Berg-Kirkpatrick
Computer Science, Mathematics
ICLR
16 January 2019

We propose an extremely simple modification to VAE training to reduce inference lag: depending on the model's current mutual information between latent variable and observation, we aggressively optimize the inference network before performing model update. Expand

DyNet: The Dynamic Neural Network Toolkit

Graham Neubig, Chris Dyer, +22 authors Pengcheng Yin
Computer Science, Mathematics
ArXiv
15 January 2017

We describe DyNet, a toolkit for implementing neural network models based on dynamic declaration of network structure. Expand

Controllable Invariance through Adversarial Feature Learning

Qizhe Xie, Zihang Dai, Yulun Du, E. Hovy, Graham Neubig
Computer Science, Mathematics
NIPS
31 May 2017

Learning meaningful representations that maintain the content necessary for a particular task while filtering away detrimental variations is a problem of great interest in machine learning. Expand

Stack-Pointer Networks for Dependency Parsing

Xuezhe Ma, Zecong Hu, J. Liu, Nanyun Peng, Graham Neubig, E. Hovy
Computer Science
ACL
3 May 2018

We introduce a novel architecture for dependency parsing: stack-pointer networks (StackPtr). Expand

Learning to Translate in Real-time with Neural Machine Translation

Graham Neubig, Kyunghyun Cho, Jiatao Gu, Victor O. K. Li
Computer Science
EACL
3 October 2016

We propose a neural machine translation (NMT) framework for simultaneous translation in which an agent learns to make decisions on when to translate from interaction with a pre-trained NMT environment. Expand

Pointwise Prediction for Robust, Adaptable Japanese Morphological Analysis

Graham Neubig, Yosuke Nakata, Shinsuke Mori
Computer Science
ACL
19 June 2011

We present a pointwise approach to Japanese morphological analysis that ignores structure information during learning and tagging. Expand

Stress Test Evaluation for Natural Language Inference

Aakanksha Naik, Abhilasha Ravichander, N. Sadeh, C. Rosé, Graham Neubig
Computer Science
COLING
2 June 2018

In this work, we propose an evaluation methodology consisting of automatically constructed "stress tests" that allow us to examine whether systems have the ability to make real inferential decisions. Expand

Learning to Generate Pseudo-Code from Source Code Using Statistical Machine Translation (T)

Yusuke Oda, Hiroyuki Fudaba, +4 authors S. Nakamura
Computer Science
30th IEEE/ACM International Conference on…
9 November 2015

Pseudo-code written in natural language can aid the comprehension of source code in unfamiliar programming languages. Expand

Recommended Authors