Daniele Paolo Radicioni

Dual PECCS: a cognitive system for conceptual representation and categorization

In this article we present an advanced version of Dual-PECCS, a cognitively-inspired knowledge representation and reasoning system aimed at extending the capabilities of artificial systems in conceptual categorization tasks. It combines different sorts of common-sense categorization (prototypical and exemplars-based categorization) with standard monotonic categorization procedures. These different types of inferential procedures are reconciled according to the tenets coming from the dual process theory of reasoning. On the other hand, from a representational perspective, the system relies on the hypothesis of conceptual structures represented as heterogeneous proxytypes. Dual-PECCS has been experimentally assessed in a task of conceptual categorization where a target concept illustrated by a simple common-sense linguistic description had to be identified by resorting to a mix of categorization strategies, and its output has been compared to human responses. The obtained results suggest that our approach can be beneficial to improve the representational and reasoning conceptual capabilities of standard cognitive artificial systems, and – in addition – that it may be plausibly applied to different general computational models of cognition. The current version of the system, in fact, extends our previous work, in that Dual- PECCS is now integrated and tested into two cognitive architectures, ACT-R and CLARION, implementing different assumptions on the underlying invariant structures governing human cognition. Such integration allowed us to extend our previous evaluation.

A knowledge-based system for prototypical reasoning

In this work we present a knowledge-based system equipped with a hybrid, cognitively inspired architecture for the representation of conceptual information. The proposed system aims at extending the classical representational and reasoning capabilities of the ontology-based frameworks towards the realm of the prototype theory. It is based on a hybrid knowledge base, composed of a classical symbolic component (grounded on a formal ontology) with a typicality based one (grounded on the conceptual spaces framework). The resulting system attempts to reconcile the heterogeneous approach to the concepts in Cognitive Science with the dual process theories of reasoning and rationality. The system has been experimentally assessed in a conceptual categorisation task where common sense linguistic descriptions were given in input, and the corresponding target concepts had to be identified. The results show that the proposed solution substantially extends the representational and reasoning ‘conceptual’ capabilities of standard ontology-based systems.

NLP-based extraction of modificatory provisions semantics

In this paper we illustrare a research based on NLP techniques aimed at automatically annotate modificatory provisions. We propose an approach which pairs deep syntactic parsing with rule-based shallow semantic analysis relying on a fine-grained taxonomy of modificatory provisions. The implemented system is evaluated on a large dataset hand-crafted by legal experts; the results are discussed and future directions of the research outlined.

TULSI: an NLP system for extracting legal modificatory provisions

In this work we present the TULSI system (so named after Turin University Legal Semantic Interpreter), a system to produce automatic annotations of normative documents through the extraction of modificatory provisions. TULSI relies on a deep syntactic analysis and a shallow semantic interpreter that are illustrated in detail. We report the results of an experimental evaluation of the system and discuss them, also suggesting future directions for further improvement.

A Resource-Driven Approach for Anchoring Linguistic Resources to Conceptual Spaces

In this paper we introduce the ttcs system, so named after Terms To Conceptual Spaces, that exploits a resource-driven approach relying on BabelNet, NASARI and ConceptNet. ttcs takes in input a term and its context of usage and produces as output a specific type of vector-based semantic representation, where conceptual information is encoded through the Conceptual Spaces a geometric framework for common-sense knowledge representation and reasoning. The system has been evaluated in a twofold experimentation. In the first case we assessed the quality of the extracted common-sense conceptual information with respect to human judgments with an online questionnaire. In the second one we compared the performances of a conceptual categorization system that was run twice, once fed with extracted annotations and once with hand-crafted annotations. In both cases the results are encouraging and provide precious insights to make substantial improvements.

From human to artificial cognition (and back)

Abstract We overview the main historical and technological elements characterising the rise, the fall and the recent renaissance of the cognitive approaches to Artificial Intelligence and provide some insights and suggestions about the future directions and challenges that, in our opinion, this discipline needs to face in the next years.

Multilevel legal ontologies

In order to manage the conceptual representation of European law we have proposed the Legal Taxonomy Syllabus (LTS) and the related methodology. In this paper we consider further issues that emerged during the testing and use of the LTS, and how we took them into account in the new release of the system. In particular, we address the problem of representing interpretation of terms besides the definitions occurring in the directives, the problem of normative change, and the process of planning legal reforms of European law. We show how to include into the Legal Taxonomy Syllabus the Acquis Principles - which have been sketched by scholars in European Private Law from the so-called Acquis communautaire -, how to take the temporal dimension into account in ontologies, and how to apply natural language processing techniques to the legal texts being annotated in the LTS.

Extracting semantic annotations from legal texts

This paper illustrates a system designed to automatically extract semantic annotations of the normative modifications present in legal texts. The work relies on a deep parsing approach. The problem of semantically annotating legal texts is cast to the problem of mapping parse trees to semantic frames representing such modifications. We report a preliminary experimentation along with the dataset employed, and discuss the results to point out future improvements.

CarpeDiem: an algorithm for the fast evaluation of SSL classifiers

In this paper we present a novel algorithm, CarpeDiem. It significantly improves on the time complexity of Viterbi algorithm, preserving the optimality of the result. This fact has consequences on Machine Learning systems that use Viterbi algorithm during learning or classification. We show how the algorithm applies to the Supervised Sequential Learning task and, in particular, to the HMPerceptron algorithm. We illustrate CarpeDiem in full details, and provide experimental results that support the proposed approach.

FrameNet model of the suspension of norms

One open problem in the AI & Law community is how to provide computers with a basic understanding of legal concepts, and their relationship with legal texts and with the legal lexicon. We propose to add a layer to connect the linguistic description of the provisions to syntactic patterns using FramNet that can be exploited thought NLP tools. A deep-parsing and shallow-semantics approach has been devised to interpret and retrieve the characterizing components of legal modificatory provisions. In this paper we single out the case of efficacy suspension and show how FrameNet approach can provide profit especially to isolate temporal parameters and their interpretation.