TULSI: an NLP system for extracting legal modificatory provisions

Lesmo, Leonardo; Mazzei, Alessandro; Palmirani, Monica; Radicioni, Daniele Paolo

doi:10.1007/s10506-012-9127-6

Cited by 15 publications

(6 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…It would not scale to handle more complex sorts of language. We defer to future work the adoption of richer language models; in particular, we will extend to the present context a deep semantic approach developed to perform IE from legal texts [20]. Despite these limitations, this approach allowed us to complete the automatization of the software pipeline going all throughout from the linguistic input description to its final conceptual categorization, thus improving the evaluation of the whole implemented system.…”

Section: Categorization Pipeline Of the Dual Process Architecturementioning

confidence: 99%

Extending Ontological Categorization Through a Dual Process Conceptual Architecture

Lieto

Radicioni

Frixione

et al. 2015

Communications in Computer and Information Science

Self Cite

View full text Add to dashboard Cite

In this work we present a hybrid knowledge representation system aiming at extending the representational and reasoning capabilities of classical ontologies by taking into account the theories of typicality in conceptual processing. The system adopts a categorization process inspired to the dual process theories and, from a representational perspective, is equipped with a heterogeneous knowledge base that couples conceptual spaces and ontological formalisms. The system has been experimentally assessed in a conceptual categorization 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 improves the representational and reasoning "conceptual" capabilities of standard ontology-based systems.

show abstract

Section: Categorization Pipeline Of the Dual Process Architecturementioning

confidence: 99%

Extending Ontological Categorization Through a Dual Process Conceptual Architecture

Lieto

Radicioni

Frixione

et al. 2015

Communications in Computer and Information Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…In this work we substantially extend the set of modificatory provisions so far considered [18] by restructuring the overall architecture of the system: that is, instead of attempting to parse each and every sentence from the 'meaningful' XML elements, we restrict the use of the parser to some sentences. Specifically, the parser is called only in case syntactic details are essential to identify the pieces of information associated to active and passive norm (see Section 2.2), and after a filtering step based on regular expressions, with beneficial effects on both accuracy and performance.…”

Section: Extraction Of Modificationsmentioning

confidence: 99%

“…The internal representation used by the system is in essence similar to that of [20,18], where modifications are represented by means of semantic frames, composed by slots [11]. In this setting, retrieving a modificatory provision amounts to choosing the frame describing that modification, and to filling its slots with the correct arguments.…”

Section: Extraction Of Modificationsmentioning

confidence: 99%

“…In past works we have explored different approaches to extract information to the ends of annotating legal documents (namely, to extract modificatory provisions): a deep-parsing approach has been carried out based on pattern matching techniques applied to parse trees [20,18]. Also, a simple though effective scheme based on compiling regular expressions has been considered [26].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Modificatory provisions detection

Gianfelice¹,

Lesmo²,

Palmirani

et al. 2013

Proceedings of the Fourteenth International Conference on Artificial Intelligence and Law

Self Cite

View full text Add to dashboard Cite

In the last few years University of Turin and CIRSFID University of Bologna collaborated to pair NLP techniques and legal knowledge to detect modificatory provisions in normative texts. Annotating these modifications is a relevant and interesting problem, in that modifications affect the whole normative system; and legal language, though more regular than unrestricted language, is sometimes particularly convoluted, and poses specific linguistic issues. This paper focuses on two major aspects. First, we explore a combination between parsing and regular expressions; to the best of our knowledge, such hybrid strategy has never been proposed before to tackle the problem at hand. Secondly, we significantly extend past works coverage (basically focussed on substitution, integration and repeal modifications) in order to account for further twelve modification kinds. For the sake of conciseness, we fully illustrate and discuss only few modification types that are more relevant and interesting: suspension, prorogation of efficacy, postponement of efficacy and exception/derogation. These sorts of modifications appear particularly challenging, in that modifications in these categories make use of similar linguistic speech acts and verbs, and exhibit strong similarities in the linguistic syntactical patterns, to such an extent that to discern them is difficult for the legal expert, too. We describe the implemented system and report about an extensive experimentation on the new modificatory provisions. Results are discussed in order to improve both system's accuracy and

show abstract

“…Como relatado em (Lesmo et al, 2013), as abordagens para identificação de eventos ou informações com base apenas em aspectos textuais podem ser melhoradas nos seus aspectos de precisão e de flexibilidade quando acrescidas de camadas adicionais de informações, tais como as geradas por elementos linguísticos ou semânticos (Dedek e Vojtas, 2011;Wimalasuriya e Dou, 2010).…”

Section: Introductionunclassified