25 citations · 89 across the 12 of their papers we have counts for
13 papers
Evolving Scientific Discovery by Unifying Data and Background Knowledge with AI Hilbert
Ryan Cory-Wright, Cristina Cornelio, Sanjeeb Dash +2
The discovery of scientific formulae that parsimoniously explain natural phenomena and align with existing background theory is a key goal in science. Historically, scientists have…
Bayesian Experimental Design for Symbolic Discovery
Kenneth L. Clarkson, Cristina Cornelio, Sanjeeb Dash +3
This study concerns the formulation and application of Bayesian optimal experimental design to symbolic discovery, which is the inference from observational data of predictive mode…
AI Descartes: Combining Data and Theory for Derivable Scientific Discovery
Cristina Cornelio, Sanjeeb Dash, Vernon Austel +6
Scientists have long aimed to discover meaningful formulae which accurately describe experimental data. A common approach is to manually create mathematical models of natural pheno…
Learning to Guide a Saturation-Based Theorem Prover
Ibrahim Abdelaziz, Maxwell Crouse, Bassem Makni +8
Traditional automated theorem provers have relied on manually tuned heuristics to guide how they perform proof search. Recently, however, there has been a surge of interest in the…
Leveraging Abstract Meaning Representation for Knowledge Base Question Answering
Pavan Kapanipathi, Ibrahim Abdelaziz, Srinivas Ravishankar +27
Knowledge base question answering (KBQA)is an important task in Natural Language Processing. Existing approaches face significant challenges including complex question understandin…
Symbolic Regression using Mixed-Integer Nonlinear Optimization
Vernon Austel, Cristina Cornelio, Sanjeeb Dash +4
The Symbolic Regression (SR) problem, where the goal is to find a regression function that does not have a pre-specified form but is any function that can be composed of a list of…
Schemaless Queries over Document Tables with Dependencies
Mustafa Canim, Cristina Cornelio, Arun Iyengar +2
Unstructured enterprise data such as reports, manuals and guidelines often contain tables. The traditional way of integrating data from these tables is through a two-step process o…
Improving Graph Neural Network Representations of Logical Formulae with Subgraph Pooling
Maxwell Crouse, Ibrahim Abdelaziz, Cristina Cornelio +4
Recent advances in the integration of deep learning with automated theorem proving have centered around the representation of logical formulae as inputs to deep learning systems. I…
A Deep Reinforcement Learning Approach to First-Order Logic Theorem Proving
Maxwell Crouse, Ibrahim Abdelaziz, Bassem Makni +7
Automated theorem provers have traditionally relied on manually tuned heuristics to guide how they perform proof search. Deep reinforcement learning has been proposed as a way to o…
Voting with Random Classifiers (VORACE): Theoretical and Experimental Analysis
Cristina Cornelio, Michele Donini, Andrea Loreggia +2
In many machine learning scenarios, looking for the best classifier that fits a particular dataset can be very costly in terms of time and resources. Moreover, it can require deep…
RuDaS: Synthetic Datasets for Rule Learning and Evaluation Tools
Cristina Cornelio, Veronika Thost
Logical rules are a popular knowledge representation language in many domains, representing background knowledge and encoding information that can be derived from given facts in a…
Using deceased-donor kidneys to initiate chains of living donor kidney paired donations: algorithms and experimentation
Cristina Cornelio, Lucrezia Furian, Antonio Nicolo' +1
We design a flexible algorithm that exploits deceased donor kidneys to initiate chains of living donor kidney paired donations, combining deceased and living donor allocation mecha…
Logical Conditional Preference Theories
Cristina Cornelio, Andrea Loreggia, Vijay Saraswat
CP-nets represent the dominant existing framework for expressing qualitative conditional preferences between alternatives, and are used in a variety of areas including constraint s…