b'Douwe Kiela'

research

∙ 09/14/2023

Anchor Points: Benchmarking Models with Much Fewer Examples

Modern language models often exhibit powerful but brittle behavior, lead...

0 Rajan Vivek, et al. ∙

research

∙ 06/28/2023

Towards Language Models That Can See: Computer Vision Through the LENS of Natural Language

We propose LENS, a modular approach for tackling computer vision problem...

0 William Berrios, et al. ∙

research

∙ 06/21/2023

OBELISC: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents

Large multimodal models trained on natural documents, which interleave i...

0 Hugo Laurençon, et al. ∙

research

∙ 03/22/2023

AfroDigits: A Community-Driven Spoken Digit Dataset for African Languages

The advancement of speech technologies has been remarkable, yet its inte...

11 Chris Chinenye Emezue, et al. ∙

research

∙ 02/14/2023

Investigating Multi-source Active Learning for Natural Language Inference

In recent years, active learning has been successfully applied to an arr...

1 Ard Snijders, et al. ∙

research

∙ 12/09/2022

Measuring Data

We identify the task of measuring data to quantitatively characterize th...

0 Margaret Mitchell, et al. ∙

research

∙ 07/20/2022

DataPerf: Benchmarks for Data-Centric AI Development

Machine learning (ML) research has generally focused on models, while th...

17 Mark Mazumder, et al. ∙

research

∙ 05/25/2022

Perturbation Augmentation for Fairer NLP

Unwanted and often harmful social biases are becoming ever more salient ...

0 Rebecca Qian, et al. ∙

research

∙ 04/07/2022

Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality

We present a novel task and dataset for evaluating the ability of vision...

3 Tristan Thrush, et al. ∙

research

∙ 04/05/2022

Dynatask: A Framework for Creating Dynamic AI Benchmark Tasks

We introduce Dynatask: an open source system for setting up custom NLP t...

0 Tristan Thrush, et al. ∙

research

∙ 12/16/2021

Models in the Loop: Aiding Crowdworkers with Generative Annotation Assistants

In Dynamic Adversarial Data Collection (DADC), human annotators are task...

0 Max Bartolo, et al. ∙

research

∙ 12/08/2021

FLAVA: A Foundational Language And Vision Alignment Model

State-of-the-art vision and vision-and-language models rely on large-sca...

2 Amanpreet Singh, et al. ∙

research

∙ 10/16/2021

Analyzing Dynamic Adversarial Training Data in the Limit

To create models that are robust across a wide range of test inputs, tra...

0 Eric Wallace, et al. ∙

research

∙ 09/08/2021

What's Hidden in a One-layer Randomly Weighted Transformer?

We demonstrate that, hidden within one-layer randomly weighted neural ne...

17 Sheng Shen, et al. ∙

research

∙ 06/04/2021

Human-Adversarial Visual Question Answering

Performance on the most commonly used Visual Question Answering dataset ...

5 Sasha Sheng, et al. ∙

research

∙ 06/02/2021

On the Efficacy of Adversarial Data Collection for Question Answering: Results from a Large-Scale Randomized Study

In adversarial data collection (ADC), a human workforce interacts with a...

0 Divyansh Kaushik, et al. ∙

research

∙ 05/24/2021

True Few-Shot Learning with Language Models

Pretrained language models (LMs) perform well on many tasks even when le...

12 Ethan Perez, et al. ∙

research

∙ 04/18/2021

Improving Question Answering Model Robustness with Synthetic Adversarial Data Generation

Despite the availability of very large datasets and pretrained models, s...

0 Max Bartolo, et al. ∙

research

∙ 04/16/2021

Cross-Modal Retrieval Augmentation for Multi-Modal Classification

Recent advances in using retrieval components over external knowledge so...

15 Shir Gur, et al. ∙

research

∙ 04/15/2021

Gradient-based Adversarial Attacks against Text Transformers

We propose the first general-purpose gradient-based attack against trans...

0 Chuan Guo, et al. ∙

research

∙ 04/15/2021

Retrieval Augmentation Reduces Hallucination in Conversation

Despite showing increasingly human-like conversational abilities, state-...

0 Kurt Shuster, et al. ∙

research

∙ 04/14/2021

Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for Little

A possible explanation for the impressive performance of masked language...

7 Koustuv Sinha, et al. ∙

research

∙ 03/14/2021

Quasi-Equivalence Discovery for Zero-Shot Emergent Communication

Effective communication is an important skill for enabling information e...

9 Kalesha Bullard, et al. ∙

research

∙ 03/05/2021

Rissanen Data Analysis: Examining Dataset Characteristics via Description Length

We introduce a method to determine if a certain capability helps to achi...

5 Ethan Perez, et al. ∙

research

∙ 12/31/2020

Learning from the Worst: Dynamically Generated Datasets to Improve Online Hate Detection

We present a first-of-its-kind large synthetic training dataset for onli...

0 Bertie Vidgen, et al. ∙

research

∙ 12/30/2020

DynaSent: A Dynamic Benchmark for Sentiment Analysis

We introduce DynaSent ('Dynamic Sentiment'), a new English-language benc...

5 Christopher Potts, et al. ∙

research

∙ 12/30/2020

Reservoir Transformer

We demonstrate that transformers obtain impressive performance even when...

23 Sheng Shen, et al. ∙

research

∙ 12/24/2020

I like fish, especially dolphins: Addressing Contradictions in Dialogue Modeling

To quantify how well natural language understanding models can capture c...

7 Yixin Nie, et al. ∙

research

∙ 12/24/2020

To what extent do human explanations of model behavior align with actual model behavior?

Given the increasingly prominent role NLP models (will) play in our live...

9 Grusha Prasad, et al. ∙

research

∙ 10/29/2020

Exploring Zero-Shot Emergent Communication in Embodied Multi-Agent Populations

Effective communication is an important skill for enabling information e...

13 Kalesha Bullard, et al. ∙

research

∙ 10/24/2020

ANLIzing the Adversarial Natural Language Inference Dataset

We perform an in-depth error analysis of Adversarial NLI (ANLI), a recen...

0 Adina Williams, et al. ∙

research

∙ 09/27/2020

Learning Optimal Representations with the Decodable Information Bottleneck

We address the question of characterizing and finding optimal representa...

16 Yann Dubois, et al. ∙

research

∙ 09/27/2020

Answering Complex Open-Domain Questions with Multi-Hop Dense Retrieval

We propose a simple and efficient multi-hop dense retrieval approach for...

0 Wenhan Xiong, et al. ∙

research

∙ 05/22/2020

Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks

Large pre-trained language models have been shown to store factual knowl...

0 Patrick Lewis, et al. ∙

research

∙ 05/10/2020

The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes

This work proposes a new challenge set for multimodal classification, fo...

7 Douwe Kiela, et al. ∙

research

∙ 05/01/2020

Multi-Dimensional Gender Bias Classification

Machine learning models are trained to find patterns in data. NLP models...

0 Emily Dinan, et al. ∙

research

∙ 02/22/2020

Unsupervised Question Decomposition for Question Answering

We aim to improve question answering (QA) by decomposing hard questions ...

14 Ethan Perez, et al. ∙

research

∙ 02/07/2020

I love your chain mail! Making knights smile in a fantasy game world: Open-domain goal-oriented dialogue agents

Dialogue research tends to distinguish between chit-chat and goal-orient...

8 Shrimai Prabhumoye, et al. ∙

research

∙ 02/07/2020

I love your chain mail! Making knights smile in a fantasy game world: Open-domain goal-orientated dialogue agents

Dialogue research tends to distinguish between chit-chat and goal-orient...

6 Shrimai Prabhumoye, et al. ∙

research

∙ 11/20/2019

Generating Interactive Worlds with Text

Procedurally generating cohesive and interesting game environments is ch...

29 Angela Fan, et al. ∙

research

∙ 11/10/2019

Queens are Powerful too: Mitigating Gender Bias in Dialogue Generation

Models often easily learn biases present in the training data, and their...

0 Emily Dinan, et al. ∙

research

∙ 10/31/2019

Adversarial NLI: A New Benchmark for Natural Language Understanding

We introduce a new large-scale NLI benchmark dataset, collected via an i...

0 Yixin Nie, et al. ∙

research

∙ 10/28/2019

Hyperbolic Graph Neural Networks

Learning from graph-structured data is an important task in machine lear...

28 Qi Liu, et al. ∙

research

∙ 10/03/2019

Generalized Inner Loop Meta-Learning

Many (but not all) approaches self-qualifying as "meta-learning" in deep...

12 Edward Grefenstette, et al. ∙

research

∙ 09/12/2019

Finding Generalizable Evidence by Learning to Convince Q A Models

We propose a system that finds the strongest supporting evidence for a g...

15 Ethan Perez, et al. ∙

research

∙ 09/10/2019

Countering Language Drift via Visual Grounding

Emergent multi-agent communication protocols are very different from nat...

0 Jason Lee, et al. ∙

research

∙ 09/06/2019

Supervised Multimodal Bitransformers for Classifying Images and Text

Self-supervised bidirectional transformer models such as BERT have led t...

19 Douwe Kiela, et al. ∙

research

∙ 07/22/2019

Why Build an Assistant in Minecraft?

In this document we describe a rationale for a research program aimed at...

2 Arthur Szlam, et al. ∙

research

∙ 03/07/2019

Learning to Speak and Act in a Fantasy Text Adventure Game

We introduce a large scale crowdsourced text adventure game as a researc...

0 Jack Urbanek, et al. ∙

research

∙ 02/22/2019

What makes a good conversation? How controllable attributes affect human judgments

A good conversation requires balance -- between simplicity and detail; s...

0 Abigail See, et al. ∙

Douwe Kiela

Featured Co-authors