
-
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...
read it
-
DynaSent: A Dynamic Benchmark for Sentiment Analysis
We introduce DynaSent ('Dynamic Sentiment'), a new English-language benc...
read it
-
Reservoir Transformer
We demonstrate that transformers obtain impressive performance even when...
read it
-
I like fish, especially dolphins: Addressing Contradictions in Dialogue Modeling
To quantify how well natural language understanding models can capture c...
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...
read it
-
Exploring Zero-Shot Emergent Communication in Embodied Multi-Agent Populations
Effective communication is an important skill for enabling information e...
read it
-
ANLIzing the Adversarial Natural Language Inference Dataset
We perform an in-depth error analysis of Adversarial NLI (ANLI), a recen...
read it
-
Learning Optimal Representations with the Decodable Information Bottleneck
We address the question of characterizing and finding optimal representa...
read it
-
Answering Complex Open-Domain Questions with Multi-Hop Dense Retrieval
We propose a simple and efficient multi-hop dense retrieval approach for...
read it
-
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
Large pre-trained language models have been shown to store factual knowl...
read it
-
The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes
This work proposes a new challenge set for multimodal classification, fo...
read it
-
Multi-Dimensional Gender Bias Classification
Machine learning models are trained to find patterns in data. NLP models...
read it
-
Unsupervised Question Decomposition for Question Answering
We aim to improve question answering (QA) by decomposing hard questions ...
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...
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...
read it
-
Generating Interactive Worlds with Text
Procedurally generating cohesive and interesting game environments is ch...
read it
-
Queens are Powerful too: Mitigating Gender Bias in Dialogue Generation
Models often easily learn biases present in the training data, and their...
read it
-
Adversarial NLI: A New Benchmark for Natural Language Understanding
We introduce a new large-scale NLI benchmark dataset, collected via an i...
read it
-
Hyperbolic Graph Neural Networks
Learning from graph-structured data is an important task in machine lear...
read it
-
Generalized Inner Loop Meta-Learning
Many (but not all) approaches self-qualifying as "meta-learning" in deep...
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...
read it
-
Countering Language Drift via Visual Grounding
Emergent multi-agent communication protocols are very different from nat...
read it
-
Supervised Multimodal Bitransformers for Classifying Images and Text
Self-supervised bidirectional transformer models such as BERT have led t...
read it
-
Why Build an Assistant in Minecraft?
In this document we describe a rationale for a research program aimed at...
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...
read it
-
What makes a good conversation? How controllable attributes affect human judgments
A good conversation requires balance -- between simplicity and detail; s...
read it
-
Inferring Concept Hierarchies from Text Corpora via Hyperbolic Embeddings
We consider the task of inferring is-a relationships from large text cor...
read it
-
The Second Conversational Intelligence Challenge (ConvAI2)
We describe the setting and results of the ConvAI2 NeurIPS competition t...
read it
-
No Training Required: Exploring Random Encoders for Sentence Classification
We explore various methods for computing sentence representations from p...
read it
-
Emergent Linguistic Phenomena in Multi-Agent Communication Games
In this work, we propose a computational framework in which agents equip...
read it
-
Jump to better conclusions: SCAN both left and right
Lake and Baroni (2018) recently introduced the SCAN data set, which cons...
read it
-
Talk the Walk: Navigating New York City through Grounded Dialogue
We introduce "Talk The Walk", the first large-scale dialogue dataset gro...
read it
-
Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometry
We are concerned with the discovery of hierarchical relationships from l...
read it
-
Hearst Patterns Revisited: Automatic Hypernym Detection from Large Text Corpora
Methods for unsupervised hypernym detection may broadly be categorized a...
read it
-
Context-Attentive Embeddings for Improved Sentence Representations
While one of the first steps in many NLP systems is selecting what embed...
read it
-
SentEval: An Evaluation Toolkit for Universal Sentence Representations
We introduce SentEval, a toolkit for evaluating the quality of universal...
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...
read it
-
Mastering the Dungeon: Grounded Language Learning by Mechanical Turker Descent
Contrary to most natural language processing research, which makes use o...
read it
-
Emergent Translation in Multi-Agent Communication
While most machine translation systems to date are trained on large para...
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...
read it
-
Learning Visually Grounded Sentence Representations
We introduce a variety of models, trained on a supervised image captioni...
read it
-
Emergent Communication in a Multi-Modal, Multi-Step Referential Game
Inspired by previous work on emergent communication in referential games...
read it
-
Poincaré Embeddings for Learning Hierarchical Representations
Representation learning has become an invaluable approach for learning f...
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...
read it
-
Virtual Embodiment: A Scalable Long-Term Strategy for Artificial Intelligence Research
Meaning has been called the "holy grail" of a variety of scientific disc...
read it
-
HyperLex: A Large-Scale Evaluation of Graded Lexical Entailment
We introduce HyperLex - a dataset and evaluation resource that quantifie...
read it