Our research integrates multiple AI technologies, including:
- Natural language processing
- Information extraction
- Knowledge representation
- Machine reasoning
- Commonsense knowledge
Building 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.
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. Learn more:
Probing Natural Language Inference Models through Semantic Fragments
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. Learn more:
Repurposing Entailment for Multi-Hop Question Answering Tasks
QASC: A Dataset for Question Answering via Sentence Composition
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. Learn more:
What's Missing: A Knowledge Gap Guided Approach for Multi-hop Question Answering
Exploiting Explicit Paths for Multi-hop Reading Comprehension
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. Learn more:
Reasoning about Actions and State Changes by Injecting Commonsense Knowledge
Everything Happens for a Reason: Discovering the Purpose of Actions in Procedural Text
To support our research and to engage others in the community, we have developed several machine reasoning datasets that exemplify the various challenges the Aristo team is currently working on. Learn more about each dataset and check out its associated leaderboard:
To both drive and showcase our research, we developed the Aristo System for answering real-world science questions. In 2019, the system achieved milestone success on the Grade 8 New York Regents Science Exams, scoring over 90% on the exams' non-diagram, multiple choice (NDMC) questions, where even three years earlier the best systems scored less than 60%. Read more about this in our article From ‘F’ to ‘A’ on the N.Y. Regents Science Exams: An Overview of the Aristo Project, and in the New York Times article A Breakthrough for AI Technology: Passing an 8th Grade Science Test.