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

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Alexander M. Rush

Alexander M. Rush

Rationales for Sequential Predictions


Sep 14, 2021
Keyon Vafa, Yuntian Deng, David M. Blei, Alexander M. Rush

Figure 1 for Rationales for Sequential Predictions
Figure 2 for Rationales for Sequential Predictions
Figure 3 for Rationales for Sequential Predictions
Figure 4 for Rationales for Sequential Predictions
* To appear in the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP 2021) 
  Access Paper or Ask Questions

Block Pruning For Faster Transformers


Sep 10, 2021
François Lagunas, Ella Charlaix, Victor Sanh, Alexander M. Rush

Figure 1 for Block Pruning For Faster Transformers
Figure 2 for Block Pruning For Faster Transformers
Figure 3 for Block Pruning For Faster Transformers
Figure 4 for Block Pruning For Faster Transformers
* EMNLP 2021. Code, hyper-parameters, evaluation results and checkpoints available at https://github.com/huggingface/nn_pruning 
  Access Paper or Ask Questions

Datasets: A Community Library for Natural Language Processing


Sep 07, 2021
Quentin Lhoest, Albert Villanova del Moral, Yacine Jernite, Abhishek Thakur, Patrick von Platen, Suraj Patil, Julien Chaumond, Mariama Drame, Julien Plu, Lewis Tunstall, Joe Davison, Mario Šaško, Gunjan Chhablani, Bhavitvya Malik, Simon Brandeis, Teven Le Scao, Victor Sanh, Canwen Xu, Nicolas Patry, Angelina McMillan-Major, Philipp Schmid, Sylvain Gugger, Clément Delangue, Théo Matussière, Lysandre Debut, Stas Bekman, Pierric Cistac, Thibault Goehringer, Victor Mustar, François Lagunas, Alexander M. Rush, Thomas Wolf

Figure 1 for Datasets: A Community Library for Natural Language Processing
Figure 2 for Datasets: A Community Library for Natural Language Processing
Figure 3 for Datasets: A Community Library for Natural Language Processing
* EMNLP Demo 2021 
  Access Paper or Ask Questions

Low-Complexity Probing via Finding Subnetworks


Apr 08, 2021
Steven Cao, Victor Sanh, Alexander M. Rush

Figure 1 for Low-Complexity Probing via Finding Subnetworks
Figure 2 for Low-Complexity Probing via Finding Subnetworks
Figure 3 for Low-Complexity Probing via Finding Subnetworks
Figure 4 for Low-Complexity Probing via Finding Subnetworks
* NAACL-HLT 2021 
  Access Paper or Ask Questions

How Many Data Points is a Prompt Worth?


Apr 06, 2021
Teven Le Scao, Alexander M. Rush

Figure 1 for How Many Data Points is a Prompt Worth?
Figure 2 for How Many Data Points is a Prompt Worth?
Figure 3 for How Many Data Points is a Prompt Worth?
Figure 4 for How Many Data Points is a Prompt Worth?
* NAACL HLT 2021 
  Access Paper or Ask Questions

Named Tensor Notation


Feb 25, 2021
David Chiang, Alexander M. Rush, Boaz Barak


  Access Paper or Ask Questions

Parameter-Efficient Transfer Learning with Diff Pruning


Dec 14, 2020
Demi Guo, Alexander M. Rush, Yoon Kim

Figure 1 for Parameter-Efficient Transfer Learning with Diff Pruning
Figure 2 for Parameter-Efficient Transfer Learning with Diff Pruning
Figure 3 for Parameter-Efficient Transfer Learning with Diff Pruning
Figure 4 for Parameter-Efficient Transfer Learning with Diff Pruning

  Access Paper or Ask Questions

Learning from others' mistakes: Avoiding dataset biases without modeling them


Dec 02, 2020
Victor Sanh, Thomas Wolf, Yonatan Belinkov, Alexander M. Rush

Figure 1 for Learning from others' mistakes: Avoiding dataset biases without modeling them
Figure 2 for Learning from others' mistakes: Avoiding dataset biases without modeling them
Figure 3 for Learning from others' mistakes: Avoiding dataset biases without modeling them
Figure 4 for Learning from others' mistakes: Avoiding dataset biases without modeling them
* 15 pages, 6 figures, 6 tables 
  Access Paper or Ask Questions

EdgeBERT: Optimizing On-Chip Inference for Multi-Task NLP


Dec 01, 2020
Thierry Tambe, Coleman Hooper, Lillian Pentecost, En-Yu Yang, Marco Donato, Victor Sanh, Alexander M. Rush, David Brooks, Gu-Yeon Wei

Figure 1 for EdgeBERT: Optimizing On-Chip Inference for Multi-Task NLP
Figure 2 for EdgeBERT: Optimizing On-Chip Inference for Multi-Task NLP
Figure 3 for EdgeBERT: Optimizing On-Chip Inference for Multi-Task NLP
Figure 4 for EdgeBERT: Optimizing On-Chip Inference for Multi-Task NLP
* 11 pages plus references 
  Access Paper or Ask Questions

Latent Template Induction with Gumbel-CRFs


Nov 29, 2020
Yao Fu, Chuanqi Tan, Bin Bi, Mosha Chen, Yansong Feng, Alexander M. Rush

Figure 1 for Latent Template Induction with Gumbel-CRFs
Figure 2 for Latent Template Induction with Gumbel-CRFs
Figure 3 for Latent Template Induction with Gumbel-CRFs
Figure 4 for Latent Template Induction with Gumbel-CRFs
* NeurIPS 2020 camera ready 
  Access Paper or Ask Questions

Sequence-Level Mixed Sample Data Augmentation


Nov 18, 2020
Demi Guo, Yoon Kim, Alexander M. Rush

Figure 1 for Sequence-Level Mixed Sample Data Augmentation
Figure 2 for Sequence-Level Mixed Sample Data Augmentation
Figure 3 for Sequence-Level Mixed Sample Data Augmentation
* EMNLP 2020 
  Access Paper or Ask Questions

Adversarial Semantic Collisions


Nov 09, 2020
Congzheng Song, Alexander M. Rush, Vitaly Shmatikov

Figure 1 for Adversarial Semantic Collisions
Figure 2 for Adversarial Semantic Collisions
Figure 3 for Adversarial Semantic Collisions
Figure 4 for Adversarial Semantic Collisions

  Access Paper or Ask Questions

Scaling Hidden Markov Language Models


Nov 09, 2020
Justin T. Chiu, Alexander M. Rush

Figure 1 for Scaling Hidden Markov Language Models
Figure 2 for Scaling Hidden Markov Language Models
Figure 3 for Scaling Hidden Markov Language Models
Figure 4 for Scaling Hidden Markov Language Models
* EMNLP 2020 
 * 9 pages, accepted as a short paper at EMNLP 2020 
  Access Paper or Ask Questions

Pre-trained Summarization Distillation


Oct 28, 2020
Sam Shleifer, Alexander M. Rush


  Access Paper or Ask Questions

Cascaded Text Generation with Markov Transformers


Jun 01, 2020
Yuntian Deng, Alexander M. Rush

Figure 1 for Cascaded Text Generation with Markov Transformers
Figure 2 for Cascaded Text Generation with Markov Transformers
Figure 3 for Cascaded Text Generation with Markov Transformers
Figure 4 for Cascaded Text Generation with Markov Transformers

  Access Paper or Ask Questions

What is Learned in Visually Grounded Neural Syntax Acquisition


May 18, 2020
Noriyuki Kojima, Hadar Averbuch-Elor, Alexander M. Rush, Yoav Artzi

Figure 1 for What is Learned in Visually Grounded Neural Syntax Acquisition
Figure 2 for What is Learned in Visually Grounded Neural Syntax Acquisition
Figure 3 for What is Learned in Visually Grounded Neural Syntax Acquisition
Figure 4 for What is Learned in Visually Grounded Neural Syntax Acquisition
* In ACL 2020 
  Access Paper or Ask Questions

Movement Pruning: Adaptive Sparsity by Fine-Tuning


May 15, 2020
Victor Sanh, Thomas Wolf, Alexander M. Rush

Figure 1 for Movement Pruning: Adaptive Sparsity by Fine-Tuning
Figure 2 for Movement Pruning: Adaptive Sparsity by Fine-Tuning
Figure 3 for Movement Pruning: Adaptive Sparsity by Fine-Tuning
Figure 4 for Movement Pruning: Adaptive Sparsity by Fine-Tuning
* 12 pages, 6 figures, 3 tables 
  Access Paper or Ask Questions

Posterior Control of Blackbox Generation


May 10, 2020
Xiang Lisa Li, Alexander M. Rush

Figure 1 for Posterior Control of Blackbox Generation
Figure 2 for Posterior Control of Blackbox Generation
Figure 3 for Posterior Control of Blackbox Generation
Figure 4 for Posterior Control of Blackbox Generation
* Accepted for publication at ACL 2020 
  Access Paper or Ask Questions

Automating Botnet Detection with Graph Neural Networks


Mar 13, 2020
Jiawei Zhou, Zhiying Xu, Alexander M. Rush, Minlan Yu

Figure 1 for Automating Botnet Detection with Graph Neural Networks
Figure 2 for Automating Botnet Detection with Graph Neural Networks
Figure 3 for Automating Botnet Detection with Graph Neural Networks
Figure 4 for Automating Botnet Detection with Graph Neural Networks
* AutoML for Networking and Systems Workshop of MLSys 2020 Conference 
 * Data and code available https://github.com/harvardnlp/botnet-detection . Accepted as a workshop paper in MLSys 2020 Conference 
  Access Paper or Ask Questions

Torch-Struct: Deep Structured Prediction Library


Feb 03, 2020
Alexander M. Rush

Figure 1 for Torch-Struct: Deep Structured Prediction Library
Figure 2 for Torch-Struct: Deep Structured Prediction Library
Figure 3 for Torch-Struct: Deep Structured Prediction Library
Figure 4 for Torch-Struct: Deep Structured Prediction Library

  Access Paper or Ask Questions

A Hierarchy of Graph Neural Networks Based on Learnable Local Features


Nov 13, 2019
Michael Lingzhi Li, Meng Dong, Jiawei Zhou, Alexander M. Rush

Figure 1 for A Hierarchy of Graph Neural Networks Based on Learnable Local Features
Figure 2 for A Hierarchy of Graph Neural Networks Based on Learnable Local Features
Figure 3 for A Hierarchy of Graph Neural Networks Based on Learnable Local Features
Figure 4 for A Hierarchy of Graph Neural Networks Based on Learnable Local Features

  Access Paper or Ask Questions

Encoder-Agnostic Adaptation for Conditional Language Generation


Sep 11, 2019
Zachary M. Ziegler, Luke Melas-Kyriazi, Sebastian Gehrmann, Alexander M. Rush

Figure 1 for Encoder-Agnostic Adaptation for Conditional Language Generation
Figure 2 for Encoder-Agnostic Adaptation for Conditional Language Generation
Figure 3 for Encoder-Agnostic Adaptation for Conditional Language Generation
Figure 4 for Encoder-Agnostic Adaptation for Conditional Language Generation

  Access Paper or Ask Questions

Neural Linguistic Steganography


Sep 03, 2019
Zachary M. Ziegler, Yuntian Deng, Alexander M. Rush

Figure 1 for Neural Linguistic Steganography
Figure 2 for Neural Linguistic Steganography
Figure 3 for Neural Linguistic Steganography
Figure 4 for Neural Linguistic Steganography
* EMNLP 2019 Accepted 
  Access Paper or Ask Questions

Commonsense Knowledge Mining from Pretrained Models


Sep 02, 2019
Joshua Feldman, Joe Davison, Alexander M. Rush

Figure 1 for Commonsense Knowledge Mining from Pretrained Models
Figure 2 for Commonsense Knowledge Mining from Pretrained Models
Figure 3 for Commonsense Knowledge Mining from Pretrained Models
Figure 4 for Commonsense Knowledge Mining from Pretrained Models

  Access Paper or Ask Questions

Compound Probabilistic Context-Free Grammars for Grammar Induction


Aug 18, 2019
Yoon Kim, Chris Dyer, Alexander M. Rush

Figure 1 for Compound Probabilistic Context-Free Grammars for Grammar Induction
Figure 2 for Compound Probabilistic Context-Free Grammars for Grammar Induction
Figure 3 for Compound Probabilistic Context-Free Grammars for Grammar Induction
Figure 4 for Compound Probabilistic Context-Free Grammars for Grammar Induction
* ACL 2019 
  Access Paper or Ask Questions

Simple Unsupervised Summarization by Contextual Matching


Jul 31, 2019
Jiawei Zhou, Alexander M. Rush

Figure 1 for Simple Unsupervised Summarization by Contextual Matching
Figure 2 for Simple Unsupervised Summarization by Contextual Matching
Figure 3 for Simple Unsupervised Summarization by Contextual Matching
Figure 4 for Simple Unsupervised Summarization by Contextual Matching
* Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2019 
  Access Paper or Ask Questions