Search Results for author:
Found 7 papers, 4 papers with code
Logical Neural Networks
We propose a novel framework seamlessly providing key properties of both neural nets (learning) and symbolic logic (knowledge and reasoning).
Leveraging Abstract Meaning Representation for Knowledge Base Question Answering
Knowledge base question answering (KBQA)is an important task in Natural Language Processing.
Logic Embeddings for Complex Query Answering
Answering logical queries over incomplete knowledge bases is challenging because: 1) it calls for implicit link prediction, and 2) brute force answering of existential first-order logic queries is exponential in the number of existential variables.
Learning to Guide a Saturation-Based Theorem Prover
In addition, to the best of our knowledge, TRAIL is the first reinforcement learning-based approach to exceed the performance of a state-of-the-art traditional theorem prover on a standard theorem proving benchmark (solving up to 17% more problems).
An Analysis of Reinforcement Learning for Malaria Control
In this work, we formally study the formulation of Malaria control and present a comprehensive analysis of several formulations used in the literature.
Proof Extraction for Logical Neural Networks
Automated Theorem Provers (ATPs) are widely used for the verification of logical statements.
An Ensemble Approach for Automated Theorem Proving Based on Efficient Name Invariant Graph Neural Representations
NIAGRA addresses this problem by using 1) improved Graph Neural Networks for learning name-invariant formula representations that is tailored for their unique characteristics and 2) an efficient ensemble approach for automated theorem proving.
