Machine Reasoning Explainability

Cyras, Kristijonas; Badrinath, Ramamurthy; Mohalik, Swarup Kumar; Mujumdar, Anusha; Nikou, Alexandros; Previti, Alessandro; Sundararajan, Vaishnavi; Feljan, Aneta Vulgarakis

doi:10.48550/arxiv.2009.00418

Cited by 2 publications

(2 citation statements)

References 116 publications

(242 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Typically, rule-based systems suffered from lack of generality, and the need for human experts to create rules in the first place. On the other hand most machine learning based approaches have the disadvantage of not being able to justify decisions taken by them in human understandable form [21], [22].…”

Section: Background and Related Workmentioning

confidence: 99%

A relational tsetlin machine with applications to natural language understanding

et al. 2022

View full text Add to dashboard Cite

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

show abstract

Section: Background and Related Workmentioning

confidence: 99%

A relational tsetlin machine with applications to natural language understanding

et al. 2022

View full text Add to dashboard Cite

show abstract

“…In parallel, Cyras et al present an extensive overview of various machine reasoning techniques employed in the domain of XAI, in which they discuss XAI techniques from symbolic AI perspective (Cyras et al 2020). The authors classify explanations into three categories.…”

Section: Related Workmentioning

confidence: 99%

Finding Counterfactual Explanations through Constraint Relaxations

Gupta¹,

Genç²,

O’Sullivan³

2022

Preprint

View full text Add to dashboard Cite

Interactive constraint systems often suffer from infeasibility (no solution) due to conflicting user constraints. A common approach to recover infeasibility is to eliminate the constraints that cause the conflicts in the system. This approach allows the system to provide an explanation as: "if the user is willing to drop out some of their constraints, there exists a solution". However, one can criticise this form of explanation as not being very informative. A counterfactual explanation is a type of explanation that can provide a basis for the user to recover feasibility by helping them understand which changes can be applied to their existing constraints rather than removing them. This approach has been extensively studied in the machine learning field, but requires a more thorough investigation in the context of constraint satisfaction. We propose an iterative method based on conflict detection and maximal relaxations in over-constrained constraint satisfaction problems to help compute a counterfactual explanation.

show abstract

Machine Reasoning Explainability

Cited by 2 publications

References 116 publications

A relational tsetlin machine with applications to natural language understanding

A relational tsetlin machine with applications to natural language understanding

Finding Counterfactual Explanations through Constraint Relaxations

Contact Info

Product

Resources

About