Build machines that read, learn and reason.
The Aristo Project aims to build systems that demonstrate a deep understanding of the world, integrating technologies for reading, learning, reasoning, and explanation.
- Natural language processing
- Information extraction
- Knowledge representation
- Machine reasoning
- Commonsense knowledge
Probing Reasoning with Language Models
Language models (LMs) have dominated much of AI recently. But what kind(s) of reasoning are they capable of? And how can they be taught to do more? We are developing analytical datasets to probe LMs and help answer these questions.
Many questions require multiple pieces of information to be combined to arrive at an answer. We are developing new multihop models capable of identifying and combining relevant facts to answer such questions.
An intelligent system should not only answer questions correctly, but also be able to explain why its answers are correct. Such a capability is essential for practical acceptance of AI technology. It is also essential for the broader goals of communicating knowledge to a user, and receiving correction from the user when the system's answer is wrong.
Reasoning about Actions
A key aspect of intelligence is being able to reason about the dynamics of the world. This requires modeling what state the world might be in, and how different actions might affect that state. Such capabilities are essential for understanding what happens during a procedure or process, for planning, and for reasoning about "what if..." scenarios.
- Bhavana Dalvi Mishra, Niket Tandon, Antoine Bosselut, Wen-tau Yih, Peter ClarkEMNLP • 2019Our goal is to better comprehend procedural text, e.g., a paragraph about photosynthesis, by not only predicting what happens, but why some actions need to happen before others. Our approach builds on a prior process comprehension framework for predicting actions' effects, to also identify… more
- Tushar Khot, Peter Clark, Michal Guerquin, Paul Edward Jansen, Ashish Sabharwal AAAI • 2020Composing knowledge from multiple pieces of texts is a key challenge in multi-hop question answering. We present a multi-hop reasoning dataset, Question Answering via Sentence Composition (QASC), that requires retrieving facts from a large corpus and composing them to answer a multiple-choice… more
- Kyle Richardson, Hai Na Hu, Lawrence S. Moss, Ashish SabharwalAAAI • 2020Do state-of-the-art models for language understanding already have, or can they easily learn, abilities such as boolean coordination, quantification, conditionals, comparatives, and monotonicity reasoning (i.e., reasoning about word substitutions in sentential contexts)? While such phenomena are… more
- Ronan Le Bras, Swabha Swayamdipta, Chandra Bhagavatula, Rowan Zellers, Matthew E. Peters, Ashish Sabharwal, Yejin Choi arXiv • 2020Large neural models have demonstrated humanlevel performance on language and vision benchmarks such as ImageNet and Stanford Natural Language Inference (SNLI). Yet, their performance degrades considerably when tested on adversarial or out-of-distribution samples. This raises the question of whether… more
- Peter Clark, Oyvind Tafjord, Kyle RichardsonarXiv • 2020AI has long pursued the goal of having systems reason over explicitly provided knowledge, but building suitable representations has proved challenging. Here we explore whether transformers can similarly learn to reason (or emulate reasoning), but using rules expressed in language, thus bypassing a… more
Recent DatasetsView All Aristo Datasets
3864 questions about open domain qualitative relationships
QuaRTz is a crowdsourced dataset of 3864 multiple-choice questions about open domain qualitative relationships. Each question is paired with one of 405 different background sentences (sometimes short paragraphs).
2771 story questions about qualitative relationships
QuaRel is a crowdsourced dataset of 2771 multiple-choice story questions, including their logical forms.
9,980 8-way multiple-choice questions about grade school science
QASC is a question-answering dataset with a focus on sentence composition. It consists of 9,980 8-way multiple-choice questions about grade school science (8,134 train, 926 dev, 920 test), and comes with a corpus of 17M sentences.
7,787 multiple choice questions annotated with question classification labels
A dataset of detailed problem domain classification labels for each of the 7,787 multiple-choice science questions found in the AI2 Reasoning Challenge (ARC) dataset, to enable targeted pairing of questions with problem-specific solvers. Also included is a taxonomy of 462 detailed problem domains for grade-school science, organized into 6 levels of specificity.
Recent PressView All Aristo Press
Paul Allen's 'Digital Aristotle' sets eyes on accomplishing practical tasks
February 5, 2020
מערכת בינה מלאכותית עברה בהצטיינות יתרה מבחן במדעים של כיתה ח' (Artificial Intelligence System Cum Laude Passed 8th Grade Science Test)
September 6, 2019
Allen Institute's Aristo AI makes breakthrough, passes eighth-grade science test
September 5, 2019
A Breakthrough for A.I. Technology: Passing an 8th-Grade Science Test
September 4, 2019
Allen Institute’s Aristo AI system finally passes an eighth-grade science test
September 4, 2019
How to tutor AI from an ‘F’ to an ‘A’
September 4, 2019
AI assistants say dumb things, and we’re about to find out why
March 14, 2018
Moving Beyond the Turing Test with the Allen AI Science Challenge
September 4, 2017