Douwe Kiela

is this you? claim profile

Research Scientist at Facebook since 2017, Postdoctoral Researcher at facebook 2016-2017, C.E.O. & Founder at Brainstorm IT from 2004-2016, Journalist/Author at Linux Magazine from 2005-2016, Research Intern at Microsoft 2015

Improving Question Answering Model Robustness with Synthetic Adversarial Data Generation

Despite the availability of very large datasets and pretrained models, s...
04/18/2021 ∙ by Max Bartolo, et al. ∙ 0 ∙ share

read it
Cross-Modal Retrieval Augmentation for Multi-Modal Classification

Recent advances in using retrieval components over external knowledge so...
04/16/2021 ∙ by Shir Gur, et al. ∙ 11 ∙ share

read it
Retrieval Augmentation Reduces Hallucination in Conversation

Despite showing increasingly human-like conversational abilities, state-...
04/15/2021 ∙ by Kurt Shuster, et al. ∙ 0 ∙ share

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

A possible explanation for the impressive performance of masked language...
04/14/2021 ∙ by Koustuv Sinha, et al. ∙ 7 ∙ share

read it
Quasi-Equivalence Discovery for Zero-Shot Emergent Communication

Effective communication is an important skill for enabling information e...
03/14/2021 ∙ by Kalesha Bullard, et al. ∙ 9 ∙ share

read it
Rissanen Data Analysis: Examining Dataset Characteristics via Description Length

We introduce a method to determine if a certain capability helps to achi...
03/05/2021 ∙ by Ethan Perez, et al. ∙ 5 ∙ share

read it
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...
12/31/2020 ∙ by Bertie Vidgen, et al. ∙ 0 ∙ share

read it
DynaSent: A Dynamic Benchmark for Sentiment Analysis

We introduce DynaSent ('Dynamic Sentiment'), a new English-language benc...
12/30/2020 ∙ by Christopher Potts, et al. ∙ 4 ∙ share

read it
Reservoir Transformer

We demonstrate that transformers obtain impressive performance even when...
12/30/2020 ∙ by Sheng Shen, et al. ∙ 23 ∙ share

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

To quantify how well natural language understanding models can capture c...
12/24/2020 ∙ by Yixin Nie, et al. ∙ 7 ∙ share

read it
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...
12/24/2020 ∙ by Grusha Prasad, et al. ∙ 9 ∙ share

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

Effective communication is an important skill for enabling information e...
10/29/2020 ∙ by Kalesha Bullard, et al. ∙ 13 ∙ share

read it
ANLIzing the Adversarial Natural Language Inference Dataset

We perform an in-depth error analysis of Adversarial NLI (ANLI), a recen...
10/24/2020 ∙ by Adina Williams, et al. ∙ 0 ∙ share

read it
Learning Optimal Representations with the Decodable Information Bottleneck

We address the question of characterizing and finding optimal representa...
09/27/2020 ∙ by Yann Dubois, et al. ∙ 16 ∙ share

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

We propose a simple and efficient multi-hop dense retrieval approach for...
09/27/2020 ∙ by Wenhan Xiong, et al. ∙ 0 ∙ share

read it
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks

Large pre-trained language models have been shown to store factual knowl...
05/22/2020 ∙ by Patrick Lewis, et al. ∙ 0 ∙ share

read it
The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes

This work proposes a new challenge set for multimodal classification, fo...
05/10/2020 ∙ by Douwe Kiela, et al. ∙ 7 ∙ share

read it
Multi-Dimensional Gender Bias Classification

Machine learning models are trained to find patterns in data. NLP models...
05/01/2020 ∙ by Emily Dinan, et al. ∙ 0 ∙ share

read it
Unsupervised Question Decomposition for Question Answering

We aim to improve question answering (QA) by decomposing hard questions ...
02/22/2020 ∙ by Ethan Perez, et al. ∙ 14 ∙ share

read it
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...
02/07/2020 ∙ by Shrimai Prabhumoye, et al. ∙ 8 ∙ share

read it
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...
02/07/2020 ∙ by Shrimai Prabhumoye, et al. ∙ 6 ∙ share

read it
Generating Interactive Worlds with Text

Procedurally generating cohesive and interesting game environments is ch...
11/20/2019 ∙ by Angela Fan, et al. ∙ 29 ∙ share

read it
Queens are Powerful too: Mitigating Gender Bias in Dialogue Generation

Models often easily learn biases present in the training data, and their...
11/10/2019 ∙ by Emily Dinan, et al. ∙ 0 ∙ share

read it
Adversarial NLI: A New Benchmark for Natural Language Understanding

We introduce a new large-scale NLI benchmark dataset, collected via an i...
10/31/2019 ∙ by Yixin Nie, et al. ∙ 0 ∙ share

read it
Hyperbolic Graph Neural Networks

Learning from graph-structured data is an important task in machine lear...
10/28/2019 ∙ by Qi Liu, et al. ∙ 28 ∙ share

read it
Generalized Inner Loop Meta-Learning

Many (but not all) approaches self-qualifying as "meta-learning" in deep...
10/03/2019 ∙ by Edward Grefenstette, et al. ∙ 12 ∙ share

read it
Finding Generalizable Evidence by Learning to Convince Q A Models

We propose a system that finds the strongest supporting evidence for a g...
09/12/2019 ∙ by Ethan Perez, et al. ∙ 15 ∙ share

read it
Countering Language Drift via Visual Grounding

Emergent multi-agent communication protocols are very different from nat...
09/10/2019 ∙ by Jason Lee, et al. ∙ 0 ∙ share

read it
Supervised Multimodal Bitransformers for Classifying Images and Text

Self-supervised bidirectional transformer models such as BERT have led t...
09/06/2019 ∙ by Douwe Kiela, et al. ∙ 19 ∙ share

read it
Why Build an Assistant in Minecraft?

In this document we describe a rationale for a research program aimed at...
07/22/2019 ∙ by Arthur Szlam, et al. ∙ 2 ∙ share

read it
Learning to Speak and Act in a Fantasy Text Adventure Game

We introduce a large scale crowdsourced text adventure game as a researc...
03/07/2019 ∙ by Jack Urbanek, et al. ∙ 0 ∙ share

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

A good conversation requires balance -- between simplicity and detail; s...
02/22/2019 ∙ by Abigail See, et al. ∙ 0 ∙ share

read it
Inferring Concept Hierarchies from Text Corpora via Hyperbolic Embeddings

We consider the task of inferring is-a relationships from large text cor...
02/03/2019 ∙ by Matt Le, et al. ∙ 0 ∙ share

read it
The Second Conversational Intelligence Challenge (ConvAI2)

We describe the setting and results of the ConvAI2 NeurIPS competition t...
01/31/2019 ∙ by Emily Dinan, et al. ∙ 2 ∙ share

read it
No Training Required: Exploring Random Encoders for Sentence Classification

We explore various methods for computing sentence representations from p...
01/29/2019 ∙ by John Wieting, et al. ∙ 0 ∙ share

read it
Emergent Linguistic Phenomena in Multi-Agent Communication Games

In this work, we propose a computational framework in which agents equip...
01/25/2019 ∙ by Laura Graesser, et al. ∙ 20 ∙ share

read it
Jump to better conclusions: SCAN both left and right

Lake and Baroni (2018) recently introduced the SCAN data set, which cons...
09/12/2018 ∙ by Joost Bastings, et al. ∙ 0 ∙ share

read it
Talk the Walk: Navigating New York City through Grounded Dialogue

We introduce "Talk The Walk", the first large-scale dialogue dataset gro...
07/09/2018 ∙ by Harm de Vries, et al. ∙ 14 ∙ share

read it
Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometry

We are concerned with the discovery of hierarchical relationships from l...
06/09/2018 ∙ by Maximilian Nickel, et al. ∙ 0 ∙ share

read it
Hearst Patterns Revisited: Automatic Hypernym Detection from Large Text Corpora

Methods for unsupervised hypernym detection may broadly be categorized a...
06/08/2018 ∙ by Stephen Roller, et al. ∙ 0 ∙ share

read it
Context-Attentive Embeddings for Improved Sentence Representations

While one of the first steps in many NLP systems is selecting what embed...
04/21/2018 ∙ by Douwe Kiela, et al. ∙ 0 ∙ share

read it
SentEval: An Evaluation Toolkit for Universal Sentence Representations

We introduce SentEval, a toolkit for evaluating the quality of universal...
03/14/2018 ∙ by Alexis Conneau, et al. ∙ 0 ∙ share

read it
Personalizing Dialogue Agents: I have a dog, do you have pets too?

Chit-chat models are known to have several problems: they lack specifici...
01/22/2018 ∙ by Saizheng Zhang, et al. ∙ 0 ∙ share

read it
Mastering the Dungeon: Grounded Language Learning by Mechanical Turker Descent

Contrary to most natural language processing research, which makes use o...
11/21/2017 ∙ by Zhilin Yang, et al. ∙ 0 ∙ share

read it
Emergent Translation in Multi-Agent Communication

While most machine translation systems to date are trained on large para...
10/12/2017 ∙ by Jason Lee, et al. ∙ 0 ∙ share

read it
Grasping the Finer Point: A Supervised Similarity Network for Metaphor Detection

The ubiquity of metaphor in our everyday communication makes it an impor...
09/02/2017 ∙ by Marek Rei, et al. ∙ 0 ∙ share

read it
Learning Visually Grounded Sentence Representations

We introduce a variety of models, trained on a supervised image captioni...
07/19/2017 ∙ by Douwe Kiela, et al. ∙ 0 ∙ share

read it
Emergent Communication in a Multi-Modal, Multi-Step Referential Game

Inspired by previous work on emergent communication in referential games...
05/29/2017 ∙ by Katrina Evtimova, et al. ∙ 0 ∙ share

read it
Poincaré Embeddings for Learning Hierarchical Representations

Representation learning has become an invaluable approach for learning f...
05/22/2017 ∙ by Maximilian Nickel, et al. ∙ 0 ∙ share

read it
Supervised Learning of Universal Sentence Representations from Natural Language Inference Data

Many modern NLP systems rely on word embeddings, previously trained in a...
05/05/2017 ∙ by Alexis Conneau, et al. ∙ 0 ∙ share

read it

Douwe Kiela

Featured Co-authors