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

 Add to Chrome

 Add to Firefox

Pre-training via Paraphrasing

Jun 26, 2020
Mike Lewis, Marjan Ghazvininejad, Gargi Ghosh, Armen Aghajanyan, Sida Wang, Luke Zettlemoyer


  Access Model/Code and Paper
Moving Down the Long Tail of Word Sense Disambiguation with Gloss-Informed Biencoders

Jun 02, 2020
Terra Blevins, Luke Zettlemoyer

* Accepted to ACL 2020; current version corrects typos and formatting 

  Access Model/Code and Paper
Active Learning for Coreference Resolution using Discrete Annotation

May 19, 2020
Belinda Z. Li, Gabriel Stanovsky, Luke Zettlemoyer

* 12 pages, 7 figures, ACL 2020 

  Access Model/Code and Paper
An Information Bottleneck Approach for Controlling Conciseness in Rationale Extraction

May 01, 2020
Bhargavi Paranjape, Mandar Joshi, John Thickstun, Hannaneh Hajishirzi, Luke Zettlemoyer


  Access Model/Code and Paper
AmbigQA: Answering Ambiguous Open-domain Questions

Apr 22, 2020
Sewon Min, Julian Michael, Hannaneh Hajishirzi, Luke Zettlemoyer


  Access Model/Code and Paper
Aligned Cross Entropy for Non-Autoregressive Machine Translation

Apr 03, 2020
Marjan Ghazvininejad, Vladimir Karpukhin, Luke Zettlemoyer, Omer Levy


  Access Model/Code and Paper
Semi-Autoregressive Training Improves Mask-Predict Decoding

Jan 23, 2020
Marjan Ghazvininejad, Omer Levy, Luke Zettlemoyer


  Access Model/Code and Paper
Multilingual Denoising Pre-training for Neural Machine Translation

Jan 23, 2020
Yinhan Liu, Jiatao Gu, Naman Goyal, Xian Li, Sergey Edunov, Marjan Ghazvininejad, Mike Lewis, Luke Zettlemoyer

* Work in progress 

  Access Model/Code and Paper
ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks

Dec 03, 2019
Mohit Shridhar, Jesse Thomason, Daniel Gordon, Yonatan Bisk, Winson Han, Roozbeh Mottaghi, Luke Zettlemoyer, Dieter Fox

* https://askforalfred.com/ 

  Access Model/Code and Paper
Knowledge Guided Text Retrieval and Reading for Open Domain Question Answering

Nov 10, 2019
Sewon Min, Danqi Chen, Luke Zettlemoyer, Hannaneh Hajishirzi


  Access Model/Code and Paper
Emerging Cross-lingual Structure in Pretrained Language Models

Nov 10, 2019
Shijie Wu, Alexis Conneau, Haoran Li, Luke Zettlemoyer, Veselin Stoyanov

* 10 pages, 7 figures, add contextual word-level alignment of monolingual BERT (v1 -> v2) 

  Access Model/Code and Paper
Zero-shot Entity Linking with Dense Entity Retrieval

Nov 10, 2019
Ledell Wu, Fabio Petroni, Martin Josifoski, Sebastian Riedel, Luke Zettlemoyer


  Access Model/Code and Paper
Enforcing Encoder-Decoder Modularity in Sequence-to-Sequence Models

Nov 09, 2019
Siddharth Dalmia, Abdelrahman Mohamed, Mike Lewis, Florian Metze, Luke Zettlemoyer


  Access Model/Code and Paper
Crowdsourcing a High-Quality Gold Standard for QA-SRL

Nov 08, 2019
Paul Roit, Ayal Klein, Daniela Stepanov, Jonathan Mamou, Julian Michael, Gabriel Stanovsky, Luke Zettlemoyer, Ido Dagan


  Access Model/Code and Paper
Unsupervised Cross-lingual Representation Learning at Scale

Nov 05, 2019
Alexis Conneau, Kartikay Khandelwal, Naman Goyal, Vishrav Chaudhary, Guillaume Wenzek, Francisco Guzmán, Edouard Grave, Myle Ott, Luke Zettlemoyer, Veselin Stoyanov

* 12 pages, 7 figures 

  Access Model/Code and Paper
Generalization through Memorization: Nearest Neighbor Language Models

Nov 01, 2019
Urvashi Khandelwal, Omer Levy, Dan Jurafsky, Luke Zettlemoyer, Mike Lewis


  Access Model/Code and Paper
BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension

Oct 29, 2019
Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Ves Stoyanov, Luke Zettlemoyer


  Access Model/Code and Paper
JuICe: A Large Scale Distantly Supervised Dataset for Open Domain Context-based Code Generation

Oct 09, 2019
Rajas Agashe, Srinivasan Iyer, Luke Zettlemoyer


  Access Model/Code and Paper
A Discrete Hard EM Approach for Weakly Supervised Question Answering

Sep 11, 2019
Sewon Min, Danqi Chen, Hannaneh Hajishirzi, Luke Zettlemoyer

* Published as a conference paper at EMNLP 2019 (long). Code available at https://github.com/shmsw25/qa-hard-em 

  Access Model/Code and Paper
Don't Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biases

Sep 09, 2019
Christopher Clark, Mark Yatskar, Luke Zettlemoyer

* In EMNLP 2019 

  Access Model/Code and Paper
BERT for Coreference Resolution: Baselines and Analysis

Sep 01, 2019
Mandar Joshi, Omer Levy, Daniel S. Weld, Luke Zettlemoyer

* EMNLP 2019 camera ready version 

  Access Model/Code and Paper
Sparse Networks from Scratch: Faster Training without Losing Performance

Aug 23, 2019
Tim Dettmers, Luke Zettlemoyer

* 9 page NeurIPS 2019 submission 

  Access Model/Code and Paper
SpanBERT: Improving Pre-training by Representing and Predicting Spans

Jul 31, 2019
Mandar Joshi, Danqi Chen, Yinhan Liu, Daniel S. Weld, Luke Zettlemoyer, Omer Levy


  Access Model/Code and Paper
RoBERTa: A Robustly Optimized BERT Pretraining Approach

Jul 26, 2019
Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, Veselin Stoyanov


  Access Model/Code and Paper
Vision-and-Dialog Navigation

Jul 19, 2019
Jesse Thomason, Michael Murray, Maya Cakmak, Luke Zettlemoyer


  Access Model/Code and Paper