Abstract
Tsetlin machines (TMs) are a pattern recognition approach that uses finite state machines for learning and propositional logic to represent patterns. In addition to being natively interpretable, they have provided competitive accuracy for various tasks. In this paper, we increase the computing power of TMs by proposing a first-order logic-based framework with Herbrand semantics. The resulting TM is relational and can take advantage of logical structures appearing in natural language, to learn rules that represent how actions and consequences are related in the real world. The outcome is a logic program of Horn clauses, bringing in a structured view of unstructured data. In closed-domain question-answering, the first-order representation produces 10 × more compact KBs, along with an increase in answering accuracy from 94.83% to 99.48%. The approach is further robust towards erroneous, missing, and superfluous information, distilling the aspects of a text that are important for real-world understanding
Highlights
Using Artificial Intelligences (AI) to answer natural language questions has long been an active research area, considered as an essential aspect in machines achieving human-level world understanding
We propose a novel relational logic based Tsetlin machines (TMs) framework to approach QA tasks systematically
Our proposed method takes advantage of noise tolerance showed by TMs to work in uncertain or ambiguous contexts
Summary
Using Artificial Intelligences (AI) to answer natural language questions has long been an active research area, considered as an essential aspect in machines achieving human-level world understanding. This paper addresses the above QA challenges by proposing a Relational Tsetlin machine (TM) that builds non-recursive first-order Horn clauses from specific examples, distilling general concepts and rules. Consider the following example of information, taken from Rajpurkar et al (2016): “The Black Death is thought to have originated in the arid plains of Central Asia, where it travelled along the Silk Road, reaching Crimea by 1343 It was most likely carried by Oriental rat fleas living on the black rats that were regular passengers on merchant ships.”One can have questions such as “Where did the black death originate?” or “How did the black death make it to the Mediterranean and Europe?”.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
