Picture for Nazneen Fatema Rajani

Nazneen Fatema Rajani

HydraSum: Disentangling Stylistic Features in Text Summarization using Multi-Decoder Models

Add code
Nov 03, 2021
Figure 1 for HydraSum: Disentangling Stylistic Features in Text Summarization using Multi-Decoder Models
Figure 2 for HydraSum: Disentangling Stylistic Features in Text Summarization using Multi-Decoder Models
Figure 3 for HydraSum: Disentangling Stylistic Features in Text Summarization using Multi-Decoder Models
Figure 4 for HydraSum: Disentangling Stylistic Features in Text Summarization using Multi-Decoder Models
Viaarxiv icon

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

Oct 14, 2021
Figure 1 for MoFE: Mixture of Factual Experts for Controlling Hallucinations in Abstractive Summarization
Figure 2 for MoFE: Mixture of Factual Experts for Controlling Hallucinations in Abstractive Summarization
Figure 3 for MoFE: Mixture of Factual Experts for Controlling Hallucinations in Abstractive Summarization
Figure 4 for MoFE: Mixture of Factual Experts for Controlling Hallucinations in Abstractive Summarization
Viaarxiv icon

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

Add code
Apr 15, 2021
Figure 1 for SummVis: Interactive Visual Analysis of Models, Data, and Evaluation for Text Summarization
Figure 2 for SummVis: Interactive Visual Analysis of Models, Data, and Evaluation for Text Summarization
Figure 3 for SummVis: Interactive Visual Analysis of Models, Data, and Evaluation for Text Summarization
Figure 4 for SummVis: Interactive Visual Analysis of Models, Data, and Evaluation for Text Summarization
Viaarxiv icon

FastIF: Scalable Influence Functions for Efficient Model Interpretation and Debugging

Add code
Dec 31, 2020
Figure 1 for FastIF: Scalable Influence Functions for Efficient Model Interpretation and Debugging
Figure 2 for FastIF: Scalable Influence Functions for Efficient Model Interpretation and Debugging
Figure 3 for FastIF: Scalable Influence Functions for Efficient Model Interpretation and Debugging
Figure 4 for FastIF: Scalable Influence Functions for Efficient Model Interpretation and Debugging
Viaarxiv icon

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

Dec 01, 2020
Figure 1 for Profile Prediction: An Alignment-Based Pre-Training Task for Protein Sequence Models
Figure 2 for Profile Prediction: An Alignment-Based Pre-Training Task for Protein Sequence Models
Figure 3 for Profile Prediction: An Alignment-Based Pre-Training Task for Protein Sequence Models
Figure 4 for Profile Prediction: An Alignment-Based Pre-Training Task for Protein Sequence Models
Viaarxiv icon

Explaining and Improving Model Behavior with k Nearest Neighbor Representations

Add code
Oct 18, 2020
Figure 1 for Explaining and Improving Model Behavior with k Nearest Neighbor Representations
Figure 2 for Explaining and Improving Model Behavior with k Nearest Neighbor Representations
Figure 3 for Explaining and Improving Model Behavior with k Nearest Neighbor Representations
Figure 4 for Explaining and Improving Model Behavior with k Nearest Neighbor Representations
Viaarxiv icon

Explaining Creative Artifacts

Oct 14, 2020
Figure 1 for Explaining Creative Artifacts
Figure 2 for Explaining Creative Artifacts
Figure 3 for Explaining Creative Artifacts
Viaarxiv icon

ReviewRobot: Explainable Paper Review Generation based on Knowledge Synthesis

Add code
Oct 13, 2020
Figure 1 for ReviewRobot: Explainable Paper Review Generation based on Knowledge Synthesis
Figure 2 for ReviewRobot: Explainable Paper Review Generation based on Knowledge Synthesis
Figure 3 for ReviewRobot: Explainable Paper Review Generation based on Knowledge Synthesis
Figure 4 for ReviewRobot: Explainable Paper Review Generation based on Knowledge Synthesis
Viaarxiv icon

Universal Natural Language Processing with Limited Annotations: Try Few-shot Textual Entailment as a Start

Add code
Oct 06, 2020
Figure 1 for Universal Natural Language Processing with Limited Annotations: Try Few-shot Textual Entailment as a Start
Figure 2 for Universal Natural Language Processing with Limited Annotations: Try Few-shot Textual Entailment as a Start
Figure 3 for Universal Natural Language Processing with Limited Annotations: Try Few-shot Textual Entailment as a Start
Figure 4 for Universal Natural Language Processing with Limited Annotations: Try Few-shot Textual Entailment as a Start
Viaarxiv icon

GeDi: Generative Discriminator Guided Sequence Generation

Add code
Sep 14, 2020
Figure 1 for GeDi: Generative Discriminator Guided Sequence Generation
Figure 2 for GeDi: Generative Discriminator Guided Sequence Generation
Figure 3 for GeDi: Generative Discriminator Guided Sequence Generation
Figure 4 for GeDi: Generative Discriminator Guided Sequence Generation
Viaarxiv icon