no code implementations • 6 Feb 2024 • Sopam Dasgupta, Farhad Shakerin, Joaquín Arias, Elmer Salazar, Gopal Gupta
In our framework, we show how counterfactual explanations are computed and justified by imagining worlds where some or all factual assumptions are altered/changed.
1 code implementation • 10 Nov 2023 • Nirmal Kumar Rout, Gyanateet Dutta, Varun Sinha, Arghadeep Dey, Subhrangshu Mukherjee, Gopal Gupta
Potholes are common road hazards that is causing damage to vehicles and posing a safety risk to drivers.
no code implementations • 23 Oct 2023 • Sopam Dasgupta, Farhad Shakerin, Joaquín Arias, Elmer Salazar, Gopal Gupta
Our approach utilizes answer set programming and the s(CASP) goal-directed ASP system.
no code implementations • 19 Oct 2023 • Parth Padalkar, Gopal Gupta
FOLD-SE-M then generates a rule-set that can be used to make predictions.
no code implementations • 20 May 2023 • Sarat Chandra Varanasi, Neeraj Mittal, Gopal Gupta
We present Locksynth, a tool that automatically derives synchronization needed for destructive updates to concurrent data structures that involve a constant number of shared heap memory write operations.
no code implementations • 15 Mar 2023 • Yankai Zeng, Abhiramon Rajasekharan, Parth Padalkar, Kinjal Basu, Joaquín Arias, Gopal Gupta
To the best of our knowledge, AutoConcierge is the first automated conversational agent that can realistically converse like a human and provide help to humans based on truly understanding human utterances.
no code implementations • 7 Feb 2023 • Abhiramon Rajasekharan, Yankai Zeng, Parth Padalkar, Gopal Gupta
NLU applications developed using the STAR framework are also explainable: along with the predicates generated, a justification in the form of a proof tree can be produced for a given output.
no code implementations • 30 Jan 2023 • Parth Padalkar, Huaduo Wang, Gopal Gupta
We evaluate the performance of our "semantic labelling algorithm" to quantify the efficacy of the semantic labelling for both the NeSy model and the NeSy-EBP model.
no code implementations • 16 Aug 2022 • Huaduo Wang, Gopal Gupta
A model with smaller number of rules and literals is easier to understand for human beings.
no code implementations • 15 Jun 2022 • Huaduo Wang, Gopal Gupta
FOLD-R++ is a new inductive learning algorithm for binary classification tasks.
2 code implementations • 14 Feb 2022 • Huaduo Wang, Farhad Shakerin, Gopal Gupta
FOLD-RM is an automated inductive learning algorithm for learning default rules for mixed (numerical and categorical) data.
no code implementations • 21 Dec 2021 • Dhruva Pendharkar, Kinjal Basu, Farhad Shakerin, Gopal Gupta
The resulting knowledge-base can then be used to perform reasoning with the help of an ASP system.
no code implementations • 22 Nov 2021 • Agostino Dovier, Andrea Formisano, Gopal Gupta, Manuel V. Hermenegildo, Enrico Pontelli, Ricardo Rocha
Since its inception, logic programming has been recognized as a programming paradigm with great potential for automated exploitation of parallelism.
no code implementations • AAAI Workshop CLeaR 2022 • Kinjal Basu, Keerthiram Murugesan, Mattia Atzeni, Pavan Kapanipathi, Kartik Talamadupula, Tim Klinger, Murray Campbell, Mrinmaya Sachan, Gopal Gupta
These rules are learned in an online manner and applied with an ASP solver to predict an action for the agent.
Inductive logic programming Natural Language Understanding +2
no code implementations • AAAI Workshop CLeaR 2022 • Huaduo Wang, Gopal Gupta
FOLD-R is an automated inductive learning algorithm for learning default rules with exceptions for mixed (numerical and categorical) data.
no code implementations • 22 Oct 2021 • Joaquín Arias, Manuel Carro, Gopal Gupta
However, the performance of existing s(CASP) implementations is not on par with other ASP systems: model consistency is checked once models have been generated, in keeping with the generate-and-test paradigm.
no code implementations • 17 Oct 2021 • Suraj Kothawade, Vinaya Khandelwal, Kinjal Basu, Huaduo Wang, Gopal Gupta
That is, while machine learning technology is good for observing and automatically understanding the surroundings of an automobile, driving decisions are better automated via commonsense reasoning rather than machine learning.
1 code implementation • 15 Oct 2021 • Huaduo Wang, Gopal Gupta
We also create a powerful tool-set by combining FOLD-R++ with s(CASP)-a goal-directed ASP execution engine-to make predictions on new data samples using the answer set program generated by FOLD-R++.
no code implementations • 11 Oct 2021 • Kinjal Basu, Huaduo Wang, Nancy Dominguez, Xiangci Li, Fang Li, Sarat Chandra Varanasi, Gopal Gupta
We present the philosophy behind CASPR's design as well as details of its implementation.
no code implementations • 26 Sep 2021 • Huaduo Wang, Farhad Shakerin, Gopal Gupta
We present a clustering- and demotion-based algorithm called Kmeans-FOLD to induce nonmonotonic logic programs from positive and negative examples.
no code implementations • 17 Sep 2021 • Fang Li, Huaduo Wang, Kinjal Basu, Elmer Salazar, Gopal Gupta
We consider the problem of finding relevant consistent concepts in a conversational AI system, particularly, for realizing a conversational socialbot.
no code implementations • 17 Sep 2021 • Sarat Chandra Varanasi, Neeraj Mittal, Gopal Gupta
We tackle the problem of automatically designing concurrent data structure operations given a sequential data structure specification and knowledge about concurrent behavior.
no code implementations • 10 Sep 2021 • Brendan Hall, Sarat Chandra Varanasi, Jan Fiedor, Joaquín Arias, Kinjal Basu, Fang Li, Devesh Bhatt, Kevin Driscoll, Elmer Salazar, Gopal Gupta
We also show how answer set programming (ASP) and its query-driven implementation s(CASP) can be used to directly realize the event calculus model of the requirements.
no code implementations • 28 Jun 2021 • Joaquín Arias, Manuel Carro, Zhuo Chen, Gopal Gupta
Automated commonsense reasoning is essential for building human-like AI systems featuring, for example, explainable AI.
no code implementations • 2 Apr 2021 • Fang Li, Huaduo Wang, Gopal Gupta
As a result, justification for why a literal is in the answer set is hard to produce.
no code implementations • 27 Jan 2021 • Kinjal Basu, Sarat Varanasi, Farhad Shakerin, Joaquin Arias, Gopal Gupta
Understanding the meaning of a text is a fundamental challenge of natural language understanding (NLU) research.
no code implementations • 22 Sep 2020 • Kinjal Basu, Sarat Chandra Varanasi, Farhad Shakerin, Gopal Gupta
We introduce a general semantics-based framework for natural language QA and also describe the SQuARE system, an application of this framework.
no code implementations • 9 Aug 2020 • Farhad Shakerin, Gopal Gupta
In our new approach, however, the data-dependent hill-climbing search is replaced with a model-dependent search where a globally optimal SVM model is trained first, then the algorithm looks into support vectors as the most influential data points in the model, and induces a clause that would cover the support vector and points that are most similar to that support vector.
1 code implementation • 24 May 2019 • Farhad Shakerin, Gopal Gupta
We present a fast and scalable algorithm to induce non-monotonic logic programs from statistical learning models.
no code implementations • 2 Aug 2018 • Farhad Shakerin, Gopal Gupta
We present a heuristic based algorithm to induce \textit{nonmonotonic} logic programs that will explain the behavior of XGBoost trained classifiers.
2 code implementations • 30 Apr 2018 • Joaquín Arias, Manuel Carro, Elmer Salazar, Kyle Marple, Gopal Gupta
The resulting model, s(CASP), can constrain variables that, as in CLP, are kept during the execution and in the answer sets.
Programming Languages Logic in Computer Science
no code implementations • 18 Feb 2018 • Farhad Shakerin, Gopal Gupta
To the best of our knowledge, this is the first heuristic-based ILP algorithm to induce answer set programs with multiple stable models.
Logic in Computer Science
1 code implementation • 1 Sep 2017 • Kyle Marple, Elmer Salazar, Gopal Gupta
We present a method for computing stable models of normal logic programs, i. e., logic programs extended with negation, in the presence of predicates with arbitrary terms.
Logic in Computer Science
no code implementations • 16 Jul 2017 • Zhuo Chen, Elmer Salazar, Kyle Marple, Gopal Gupta, Lakshman Tamil, Sandeep Das, Alpesh Amin
A standard approach to managing chronic diseases by medical community is to have a committee of experts develop guidelines that all physicians should follow.
1 code implementation • 10 Jul 2017 • Farhad Shakerin, Elmer Salazar, Gopal Gupta
An approach through recursively finding patterns in exceptions turns out to correspond to the problem of learning default theories.
Logic in Computer Science
no code implementations • 25 Oct 2016 • Zhuo Chen, Kyle Marple, Elmer Salazar, Gopal Gupta, Lakshman Tamil
In this paper we describe a physician-advisory system for CHF management that codes the entire set of clinical practice guidelines for CHF using answer set programming.