Share This Author
AllenNLP: A Deep Semantic Natural Language Processing Platform
AllenNLP is described, a library for applying deep learning methods to NLP research that addresses issues with easy-to-use command-line tools, declarative configuration-driven experiments, and modular NLP abstractions.
Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
A new question set, text corpus, and baselines assembled to encourage AI research in advanced question answering constitute the AI2 Reasoning Challenge (ARC), which requires far more powerful knowledge and reasoning than previous challenges such as SQuAD or SNLI.
UnifiedQA: Crossing Format Boundaries With a Single QA System
This work uses the latest advances in language modeling to build a single pre-trained QA model, UNIFIEDQA, that performs well across 19 QA datasets spanning 4 diverse formats, and results in a new state of the art on 10 factoid and commonsense question answering datasets.
SUSY and Goliath
We investigate the ``giant gravitons'' of McGreevy, Susskind and Toumbas . We demonstrate that these are BPS configurations which preserve precisely the same supersymmetries as a ``point-like''…
Transformers as Soft Reasoners over Language
This work trains transformers to reason (or emulate reasoning) over natural language sentences using synthetically generated data, thus bypassing a formal representation and suggesting a new role for transformers, namely as limited "soft theorem provers" operating over explicit theories in language.
Superstars and giant gravitons
We examine a family of BPS solutions of ten-dimensional type-IIB supergravity. These solutions asymptotically approach AdS5 × S5 and carry internal `angular' momentum on the five-sphere. While a…
The Noncommutative bion core
We examine noncommutative solutions of the non-Abelian theory on the world-volume of N coincident D-strings. These solutions can be interpreted in terms of noncommutative geometry as funnels…
Combining Retrieval, Statistics, and Inference to Answer Elementary Science Questions
This paper describes an alternative approach that operates at three levels of representation and reasoning: information retrieval, corpus statistics, and simple inference over a semi-automatically constructed knowledge base, to achieve substantially improved results.
Reasoning Over Paragraph Effects in Situations
This work presents ROPES, a challenging benchmark for reading comprehension targeting Reasoning Over Paragraph Effects in Situations, and targets expository language describing causes and effects, as they have clear implications for new situations.
ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Language
This work shows that a generative model, called ProofWriter, can reliably generate both implications of a theory and the natural language proofs that support them, and shows that generative techniques can perform a type of abduction with high precision.