Translating Simple Legal Text to Formal Representations

Gaur, Shruti; Vo, Nguyen; Kashihara, Kazuaki; Baral, Chitta

doi:10.1007/978-3-662-48119-6_19

Cited by 8 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…[34] extracts deontic rules from legislation using a rule-based approach, based on annotated legal texts. [9] built a system to translate simple sentences to various logical representations. [7] used a combination of approaches, including tree parsers, to parse rules form legislation.…”

Section: Related Workmentioning

confidence: 99%

From Text to Structure: Using Large Language Models to Support the Development of Legal Expert Systems

Janatian,

Westermann,

Tan

et al. 2023

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

Encoding legislative text in a formal representation is an important prerequisite to different tasks in the field of AI & Law. For example, rule-based expert systems focused on legislation can support laypeople in understanding how legislation applies to them and provide them with helpful context and information. However, the process of analyzing legislation and other sources to encode it in the desired formal representation can be time-consuming and represents a bottleneck in the development of such systems. Here, we investigate to what degree large language models (LLMs), such as GPT-4, are able to automatically extract structured representations from legislation. We use LLMs to create pathways from legislation, according to the JusticeBot methodology for legal decision support systems, evaluate the pathways and compare them to manually created pathways. The results are promising, with 60% of generated pathways being rated as equivalent or better than manually created ones in a blind comparison. The approach suggests a promising path to leverage the capabilities of LLMs to ease the costly development of systems based on symbolic approaches that are transparent and explainable.

show abstract

Section: Related Workmentioning

confidence: 99%

From Text to Structure: Using Large Language Models to Support the Development of Legal Expert Systems

Janatian,

Westermann,

Tan

et al. 2023

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

show abstract

“…Instead of using pattern matching methods based on lexico-syntactic patterns, they proposed to adopt syntactic dependencies between terms extracted with a syntactic parser, which is also the approach used in [8], but with different kinds of information extracted. [12] developed a translation systems to learn the semantics of unknown words from syntactically similar words with known meanings, which is able to translate into a variety of formal language representations. As mentioned by the authors, their method needs to be tested with a bigger corpus.…”

Section: Related Workmentioning

confidence: 99%

Automatic Extraction of Legal Norms: Evaluation of Natural Language Processing Tools

Ferraro

Lam

Tosatto

et al. 2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Extracting and formalising legal norms from legal documents is a time-consuming and complex procedure. Therefore, the automatic methods that can accelerate this process are in high demand. In this paper, we address two major questions related to this problem: (i) what are the challenges in formalising legal documents into a machine understandable formalism? (ii) to what extent can the data-driven state-of-the-art approaches developed in the Natural Language Processing (NLP) community be used to automate the normative mining process. The results of our experiments indicate that NLP technologies such as relation extraction and semantic parsing are promising research avenues to advance research in this area.

show abstract

“…R. Taber [19]). When preparing translators, teachers are advised to pay special attention not only to the difficulty of understanding but to the difficulty of expressing the original thought in the translating language (S. Wurm [30], S. Gaur, N.H. Vo, K. Kashihara, C. Baral [17]). According to I.A.…”

Section: Introductionmentioning

confidence: 99%

Development of professional competences of students – future translators in the Skopos Theory framework

Akasheva¹,

Rakhimova²,

Smolnikov³

2022

P Sci Edu

View full text Add to dashboard Cite

Introduction. The development of the translation services market in modern conditions, presents new challenges in improving the quality of education in the training courses of "Translation and Translation Studies" and "Linguistics" in accordance with the Federal Educational Standard of Higher Education (FSE) and the Professional Standard. This fully correlates with the international requirements for translation, formulated by the UN Department of General Assembly Affairs. The development of professional translation competences becomes urgent, which requires new approaches to the professional training of future translators. It is impossible to effectively teach translation based only on linguistic translation algorithms, since the translation competence is not formed automatically in the course of language competence development. Materials and methods. The research methodology is based on competence and professionally oriented approaches to translation teaching. The main research methods are the analysis of Russian and foreign scientists’ research on the problem of translation teaching, theoretical analysis of works on translation theory and Skopos Theory, observation, text analysis and generalization of teaching experience. Research results. In the course of the research, based on our own translation experience and on Ch. Nord's didactic principles, the selected texts for translation, including pragmatic, conventional, linguistic, regulatory problems, were analyzed and a scheme for pre-translation text analysis and approaches to assessing the quality of translations were also developed. Conclusion. The linguistic approach to the implementation of translation does not allow us to successfully fulfill the requirements for the quality of translation, since translation requires taking into account the aspects arising from the purpose of the translation and the specific translation situation. The inclusion in the process of teaching translation of texts with carefully selected translation problems, and purposeful work on these problems enable future translators to solve translation tasks more effectively. The scheme of pre-translation text analysis and the approaches to assessing the quality of translation developed and presented in this article can be used to evaluate any other kind of translation.

show abstract

Translating Simple Legal Text to Formal Representations

Cited by 8 publications

References 14 publications

From Text to Structure: Using Large Language Models to Support the Development of Legal Expert Systems

From Text to Structure: Using Large Language Models to Support the Development of Legal Expert Systems

Automatic Extraction of Legal Norms: Evaluation of Natural Language Processing Tools

Development of professional competences of students – future translators in the Skopos Theory framework

Contact Info

Product

Resources

About