Timezone: »
Statistical Relational Learning (SRL) methods are the most widely used techniques to generate distributional representations of the symbolic Knowledge Bases (KBs). These methods embed any given KB into a vector space by exploiting statistical similarities among its entities and predicates but without any guarantee of preserving the underlying logical structure of the KB. This, in turn, results in poor performance of logical reasoning tasks that are solved using such distributional representations. We present a novel approach called Embed2Reason (E2R) that embeds a symbolic KB into a vector space in a logical structure preserving manner. This approach is inspired by the theory of Quantum Logic. Such an embedding allows answering membership based complex logical reasoning queries with impressive accuracy improvements over popular SRL baselines.
Author Information
Dinesh Garg (IBM Research AI, India)
Shajith Ikbal Mohamed (IBM Research AI, India)
Santosh Kumar Srivastava (IBM Research AI)
Harit Vishwakarma (University of Wisconsin Madison)
Hima Karanam (IBM Research AI)
L Venkata Subramaniam (IBM Research AI - India)
More from the Same Authors
-
2022 : Image Manipulation via Neuro-Symbolic Networks »
Harman Singh · Poorva Garg · Mohit Gupta · Kevin Shah · Arnab Kumar Mondal · Dinesh Khandelwal · Parag Singla · Dinesh Garg -
2022 Poster: Lifting Weak Supervision To Structured Prediction »
Harit Vishwakarma · Frederic Sala -
2020 Poster: Attack of the Tails: Yes, You Really Can Backdoor Federated Learning »
Hongyi Wang · Kartik Sreenivasan · Shashank Rajput · Harit Vishwakarma · Saurabh Agarwal · Jy-yong Sohn · Kangwook Lee · Dimitris Papailiopoulos -
2020 Poster: Optimal Lottery Tickets via Subset Sum: Logarithmic Over-Parameterization is Sufficient »
Ankit Pensia · Shashank Rajput · Alliot Nagle · Harit Vishwakarma · Dimitris Papailiopoulos -
2020 Poster: Inductive Quantum Embedding »
Santosh Kumar Srivastava · Dinesh Khandelwal · Dhiraj Madan · Dinesh Garg · Hima Karanam · L Venkata Subramaniam -
2020 Spotlight: Optimal Lottery Tickets via Subset Sum: Logarithmic Over-Parameterization is Sufficient »
Ankit Pensia · Shashank Rajput · Alliot Nagle · Harit Vishwakarma · Dimitris Papailiopoulos