Taylor Berg-Kirkpatrick

Publications
Influence

Painless Unsupervised Learning with Features

Taylor Berg-Kirkpatrick, A. Bouchard-Côté, John DeNero, D. Klein
Computer Science
HLT-NAACL
2 June 2010

We show how features can easily be added to standard generative models for unsupervised learning, without requiring complex new training methods. Expand

Speaker-Follower Models for Vision-and-Language Navigation

Daniel Fried, Ronghang Hu, +7 authors Trevor Darrell
Computer Science
NeurIPS
1 June 2018

We propose an approach to vision-and-language navigation that addresses both these issues with an embedded speaker model and a panoramic action space. Expand

Learning Bilingual Lexicons from Monolingual Corpora

A. Haghighi, Percy Liang, Taylor Berg-Kirkpatrick, D. Klein
Computer Science
ACL
1 June 2008

We present a method for learning bilingual translation lexicons from monolingual corpora. Expand

Learning Whom to Trust with MACE

Dirk Hovy, Taylor Berg-Kirkpatrick, Ashish Vaswani, E. Hovy
Computer Science
HLT-NAACL
1 June 2013

We build a generative model of the annotation process that learns in an unsupervised fashion to identify which annotators are trustworthy and predict the correct underlying labels. Expand

Improved Variational Autoencoders for Text Modeling using Dilated Convolutions

Zichao Yang, Zhiting Hu, R. Salakhutdinov, Taylor Berg-Kirkpatrick
Computer Science
ICML
27 February 2017

We show that with the right decoder, VAE can outperform LSTM language models for generative modeling of text. Expand

Jointly Learning to Extract and Compress

Taylor Berg-Kirkpatrick, Daniel Gillick, D. Klein
Computer Science
ACL
19 June 2011

We learn a joint model of sentence extraction and compression for multi-document summarization. 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

Unsupervised Text Style Transfer using Language Models as Discriminators

Zichao Yang, Zhiting Hu, Chris Dyer, E. Xing, Taylor Berg-Kirkpatrick
Computer Science
NeurIPS
30 May 2018

We use a language model as the discriminator in GAN-based unsupervised style transfer systems to ensure that transferred sentences are similar to sentences in the target domain. Expand

An Empirical Investigation of Statistical Significance in NLP

Taylor Berg-Kirkpatrick, David Burkett, D. Klein
Computer Science
EMNLP-CoNLL
12 July 2012

We investigate two aspects of the empirical behavior of paired significance tests for NLP systems. Expand

Learning-Based Single-Document Summarization with Compression and Anaphoricity Constraints

Greg Durrett, Taylor Berg-Kirkpatrick, D. Klein
Computer Science
ACL
29 March 2016

We present a discriminative model for single-document summarization that integrally combines compression and anaphoricity constraints. Expand

Recommended Authors