Research - Papers
Explore a selection of our published work on a variety of key research challenges in AI.
ZEST: Zero-shot Learning from Text Descriptions using Textual Similarity and Visual Summarization
We study the problem of recognizing visual entities from the textual descriptions of their classes. Specifically, given birds' images with free-text descriptions of their species, we learn to…
Generative Data Augmentation for Commonsense Reasoning
Recent advances in commonsense reasoning depend on large-scale human-annotated training data to achieve peak performance. However, manual curation of training examples is expensive and has been…
Evaluating Models' Local Decision Boundaries via Contrast Sets
Standard test sets for supervised learning evaluate in-distribution generalization. Unfortunately, when a dataset has systematic gaps (e.g., annotation artifacts), these evaluations are misleading:…
What's Missing: A Knowledge Gap Guided Approach for Multi-hop Question Answering
Multi-hop textual question answering requires combining information from multiple sentences. We focus on a natural setting where, unlike typical reading comprehension, only partial information is…
Evaluating Question Answering Evaluation
As the complexity of question answering (QA) datasets evolve, moving away from restricted formats like span extraction and multiple-choice (MC) to free-form answer generation, it is imperative to…
On Making Reading Comprehension More Comprehensive
Machine reading comprehension, the task of evaluating a machine’s ability to comprehend a passage of text, has seen a surge in popularity in recent years. There are many datasets that are targeted…
ORB: An Open Reading Benchmark for Comprehensive Evaluation of Machine Reading Comprehension
Reading comprehension is one of the crucial tasks for furthering research in natural language understanding. A lot of diverse reading comprehension datasets have recently been introduced to study…
Reasoning Over Paragraph Effects in Situations
A key component of successfully reading a passage of text is the ability to apply knowledge gained from the passage to a new situation. In order to facilitate progress on this kind of reading, we…
A Discrete Hard EM Approach for Weakly Supervised Question Answering
Many question answering (QA) tasks only provide weak supervision for how the answer should be computed. For example, TriviaQA answers are entities that can be mentioned multiple times in supporting…
AllenNLP Interpret: A Framework for Explaining Predictions of NLP Models
Neural NLP models are increasingly accurate but are imperfect and opaque---they break in counterintuitive ways and leave end users puzzled at their behavior. Model interpretation methods ameliorate…