Search Results for author: Jesse Vig

Found 12 papers, 6 papers with code

Exploring Neural Models for Query-Focused Summarization

1 code implementation14 Dec 2021 Jesse Vig, Alexander R. Fabbri, Wojciech Kryściński, Chien-Sheng Wu, Wenhao Liu

Query-focused summarization (QFS) aims to produce summaries that answer particular questions of interest, enabling greater user control and personalization.

MoFE: Mixture of Factual Experts for Controlling Hallucinations in Abstractive Summarization

no code implementations14 Oct 2021 Prafulla Kumar Choubey, Jesse Vig, Wenhao Liu, Nazneen Fatema Rajani

We train our experts using reinforcement learning (RL) to minimize the error defined by two factual consistency metrics: entity overlap and dependency arc entailment.

Abstractive Text Summarization

SummVis: Interactive Visual Analysis of Models, Data, and Evaluation for Text Summarization

1 code implementation ACL 2021 Jesse Vig, Wojciech Kryściński, Karan Goel, Nazneen Fatema Rajani

Novel neural architectures, training strategies, and the availability of large-scale corpora haven been the driving force behind recent progress in abstractive text summarization.

Abstractive Text Summarization

Robustness Gym: Unifying the NLP Evaluation Landscape

2 code implementations NAACL 2021 Karan Goel, Nazneen Rajani, Jesse Vig, Samson Tan, Jason Wu, Stephan Zheng, Caiming Xiong, Mohit Bansal, Christopher Ré

Despite impressive performance on standard benchmarks, deep neural networks are often brittle when deployed in real-world systems.

Entity Linking

Profile Prediction: An Alignment-Based Pre-Training Task for Protein Sequence Models

no code implementations1 Dec 2020 Pascal Sturmfels, Jesse Vig, Ali Madani, Nazneen Fatema Rajani

Recent deep-learning approaches to protein prediction have shown that pre-training on unlabeled data can yield useful representations for downstream tasks.

Language Modelling

BERTology Meets Biology: Interpreting Attention in Protein Language Models

2 code implementations ICLR 2021 Jesse Vig, Ali Madani, Lav R. Varshney, Caiming Xiong, Richard Socher, Nazneen Fatema Rajani

Transformer architectures have proven to learn useful representations for protein classification and generation tasks.

Causal Mediation Analysis for Interpreting Neural NLP: The Case of Gender Bias

1 code implementation26 Apr 2020 Jesse Vig, Sebastian Gehrmann, Yonatan Belinkov, Sharon Qian, Daniel Nevo, Simas Sakenis, Jason Huang, Yaron Singer, Stuart Shieber

Common methods for interpreting neural models in natural language processing typically examine either their structure or their behavior, but not both.

A Multiscale Visualization of Attention in the Transformer Model

3 code implementations ACL 2019 Jesse Vig

The Transformer is a sequence model that forgoes traditional recurrent architectures in favor of a fully attention-based approach.

Analyzing the Structure of Attention in a Transformer Language Model

no code implementations WS 2019 Jesse Vig, Yonatan Belinkov

The Transformer is a fully attention-based alternative to recurrent networks that has achieved state-of-the-art results across a range of NLP tasks.

Language Modelling

Visualizing Attention in Transformer-Based Language Representation Models

no code implementations4 Apr 2019 Jesse Vig

We present an open-source tool for visualizing multi-head self-attention in Transformer-based language representation models.

Language Modelling

Cannot find the paper you are looking for? You can Submit a new open access paper.