Project

Back to overview

AutoLegis: Automated detection of styleguide violations in legislative drafts

Applicant Hess Michael
Number 134701
Funding scheme Project funding (Div. I-III)
Research institution Institut für Computerlinguistik Universität Zürich
Institution of higher education University of Zurich - ZH
Main discipline German and English languages and literature
Start/End 01.05.2011 - 28.02.2015
Approved amount 384'406.00
Show all

All Disciplines (3)

Discipline
German and English languages and literature
Information Technology
Legal sciences

Keywords (5)

Natural Language Processing; Legislative Drafting; Authoring Tools; Automated Style Checking; Legal Linguistics

Lay Summary (German)

Lead
Entwürfe von Gesetzestexten müssen mehrere redaktionelle Zyklendurchlaufen, bevor sie puliziert werden. Die Texte müssen nicht nur rechtlichen Kriterien genügen, sondern auch sprachlichen Richtlinien enstprechen.
Lay summary

Eine manuelle Überprüfung der Übereinstimmung von Gesetzesentwürfen mit diesen Richtlinien ist ausgesprochen zeitaufwändig und fehleranfällig. In diesem Projekt wird erforscht, wie dieser Prozess teilweise automatisiert werden kann: Verletzungen von sprachlichen Richtlinien sollen von einem Computerprogramm automatisch erkannt und entsprechende Fehlerhinweise für den Gesetzesredaktor oder die Gesetzesredaktorin generiert werden.

Direct link to Lay Summary Last update: 19.02.2015

Lay Summary (English)

Lead
Drafts of legislative texts have to go through several editorial cycles before they are published. The texts not only have to comply with legal aspects but also with linguistic guidelines.
Lay summary

Manual assessment of the compliance of legislative texts with these guidelines is extremely time-consuming and error-prone. This project investigates how this process can be partially automatised: guideline violations shall be detected automatically by a computer program and corresponding feedback shall be generated for the editor.

 

 

Direct link to Lay Summary Last update: 19.02.2015

Responsible applicant and co-applicants

Employees

Publications

Publication
Supertagging for Domain Adaptation: An Approach with Law Texts
Sugisaki Kyoko (2017), Supertagging for Domain Adaptation: An Approach with Law Texts, in The 16th International Conference on Artificial Intelligence and Law, LondonICAIL, London.
Towards Data-Driven Style Checking: An Example for Law Texts
Sugisaki Kyoko (2016), Towards Data-Driven Style Checking: An Example for Law Texts, in 29th International Conference on Legal Knowledge and Information Systems, NizaJurix, Niza.
Between conciseness and transparency: Presuppositions in legislative texts
Höfler Stefan (2014), Between conciseness and transparency: Presuppositions in legislative texts, in International Journal for the Semiotics of Law, 27(4), 627-644.
Bilingwis: ein statistikbasiertes Konkordanzsystem für die Systematische Rechtssammlung des Bundes
Weibel Manuela (2014), Bilingwis: ein statistikbasiertes Konkordanzsystem für die Systematische Rechtssammlung des Bundes, in Leges: Gesetzgebung & Evaluation, 25(1), 285-291.
Constructing and exploiting an automatically annotated resource of legislative texts
Höfler Stefan, Sugisaki Kyokko (2014), Constructing and exploiting an automatically annotated resource of legislative texts, in Ninth International Conference on Language Resources and Evaluation (LREC'14), Reykjavik-, -.
Incremental morphosyntactic disambiguation of nouns in German-language law texts
Sugisaki Kyoko, Höfler Stefan (2013), Incremental morphosyntactic disambiguation of nouns in German-language law texts, in ESSLLI-13 Workshop on Extrinsic Parse Improvement (EPI), DüsseldorfESSLI, Düsseldorf.
Verbal morphosyntactic disambiguation through topological field recognition in German-language law texts
Sugisaki Kyoko, Höfler Stefan (2013), Verbal morphosyntactic disambiguation through topological field recognition in German-language law texts, in Mahlow Cerstin (ed.), Springer, Berlin/Heidelberg, 136-147.
«Ein Artikel – eine Norm». Redaktionelle Überlegungen zur Diskursstruktur von Gesetzesartikeln
Höfler Stefan (2012), «Ein Artikel – eine Norm». Redaktionelle Überlegungen zur Diskursstruktur von Gesetzesartikeln, in LeGes: Gesetzgebung & Evaluation, 23(3), 311-335.
From drafting guideline to error detection: Automating style checking for legislative texts
Höfler Stefan, Sugisaki Kyoko (2012), From drafting guideline to error detection: Automating style checking for legislative texts, in Proceedings of the EACL 2012 Workshop on Computational Linguistics and Writing, AvignonEACL, Avignon.
Legislative drafting guidelines: How different are they from controlled language rules for technical writing?
Höfler Stefan (2012), Legislative drafting guidelines: How different are they from controlled language rules for technical writing?, in Kuhn Tobias (ed.), Springer, Berlin/Heidelberg, 138-151.
«Ein Satz – eine Aussage». Multipropositionale Rechtssätze an der Sprache erkennen
Höfler Stefan (2011), «Ein Satz – eine Aussage». Multipropositionale Rechtssätze an der Sprache erkennen, in Leges: Gesetzgebung & Evalutation, 22(2), 275-295.
Building corpora for the philological study of Swiss legal texts
Höfler Stefan, Piotrowski Michael (2011), Building corpora for the philological study of Swiss legal texts, in Journal for Language Technology and Computational Linguistics, 26(2), 77-89.
Detecting legal definitions for automated style checking in draft laws
Höfler Stefan, Bünzli Alexandra, Sugisaki Kyoko (2011), Detecting legal definitions for automated style checking in draft laws, in Technical Reports in Computational Linguistics CL-2011.01, ZürichUZH, Zürich.
Review of: Grewendorf, Günther/Rathert, Monika, eds. (2009): Formal Linguistics and Law
Höfler Stefan (2011), Review of: Grewendorf, Günther/Rathert, Monika, eds. (2009): Formal Linguistics and Law, in Fachsprache: International Journal for Specialized Communication, 34(3–4), 230-233.

Collaboration

Group / person Country
Types of collaboration
Schweizerische Bundeskanzlei, Zentrale Sprachdienste, Sektion Deutsch Switzerland (Europe)
- in-depth/constructive exchanges on approaches, methods or results

Scientific events

Active participation

Title Type of contribution Title of article or contribution Date Place Persons involved
Ninth International Conference on Language Resources and Evaluation (LREC'14) Poster Constructing and exploiting an automatically annotated resource of legislative texts 26.05.2014 Reykjavik, Iceland Sugisaki Kyoko;
Kolloquium in Computerlinguistik FS 2014 Individual talk Automatic detection of syntax-related style violations in law texts 06.05.2014 Zürich, Switzerland Sugisaki Kyoko;
Jahrestagung 2014 der Vereinigung für Angewandte Linguistik in der Schweiz (VALS) Talk given at a conference «Ein Satz – eine Aussage»: Umsetzung in der Gesetzesredaktion 12.02.2014 Lugano, Switzerland Höfler Stefan;
Third International Workshop on Systems and Frameworks for Computational Morphology (SFCM 2013) Talk given at a conference Verbal morphosyntactic disambiguation through topological field recognition in German-language law texts 06.09.2013 Berlin, Germany Sugisaki Kyoko;
ESSLLI-13 Workshop on Extrinsic Parse Improvement (EPI) Talk given at a conference Incremental Morphosyntactic Disambiguation of Nouns in German-Language Law Texts 13.08.2013 Düsseldorf, Germany Sugisaki Kyoko;
Kolloquium in Computerlinguistik FS 2013 Individual talk Morphosyntaktische Desambiguierung von Nomen in Schweizer Gesetzestexten 19.03.2013 Zürich, Switzerland Sugisaki Kyoko;
35. Jahrestagung der Deutschen Gesellschaft für Sprachwissenschaft (DGfS) Poster Hybrid Morphosyntactic Disambiguation for Parsing Swiss Law Texts in German 14.03.2013 Potsdam, Germany Sugisaki Kyoko;
Third International Workshop on Controlled Natural Language (CNL 2012) Poster Automated Style Checking for Swiss Laws 30.08.2012 Zürich, Switzerland Höfler Stefan;
Third International Workshop on Controlled Natural Language (CNL 2012) Talk given at a conference Legislative Drafting Guidelines: How Different Are They From Controlled Language Rules for Technical Writing? 30.08.2012 Zürich, Switzerland Höfler Stefan;
EACL 2012 Workshop on Computational Linguistics and Writing Talk given at a conference Challenges in Automating Style Checking for Legislative Texts 23.04.2012 Avignon, France Sugisaki Kyoko;
Kolloquium in Computerlinguistik FS 2012 Individual talk Modellierung von Verletzungen syntaktischer Stilregeln in Gesetzestexten 17.04.2012 Zürich, Switzerland Sugisaki Kyoko;
Workshop on Annotation of Corpora for Research in the Humanities Talk given at a conference Building Corpora for the Philological Study of Swiss Legal Texts 05.01.2012 Heidelberg, Germany Höfler Stefan;
Linguistisches Forschungskolloquium Individual talk Erkennung von Stilrichtlinienverletzungen in Gesetzestexten 20.10.2011 Zürich, Switzerland Höfler Stefan;


Self-organised

Title Date Place
Kolloquium in Computerlinguistik: Stilprüfung & Rechtstextanalyse 21.04.2012 Zürich (Switzerland), Switzerland

Knowledge transfer events

Active participation

Title Type of contribution Date Place Persons involved
Redaktionstag des deutschen Sprachdienstes der Schweizerischen Bundeskanzlei Talk 17.09.2013 Guggisberg, Switzerland Höfler Stefan;


Communication with the public

Communication Title Media Place Year
New media (web, blogs, podcasts, news feeds etc.) Webseite: «Bilingwis: finding translations in bilingual context (Schweizerische Gesetzestexte)» Web German-speaking Switzerland International 2014
New media (web, blogs, podcasts, news feeds etc.) Webseite «Domänenspezifische maschinelle Stilprüfung für Gesetzestexte» Web International German-speaking Switzerland 2011

Awards

Title Year
Candoc (Forschungskredit der UZH) 2014

Associated projects

Number Title Start Funding scheme
154951 Der textuelle Aufbau von Gesetzesartikeln - Textlinguistische Modelle im Dienste der Rechtsetzungslehre 01.03.2015 Ambizione
176717 Handlungsformen der Gesetzessprache: Untersuchungen zur Text- und Satzpragmatik der Gesetzesredaktion am Beispiel von Gesetzestexten des schweizerischen Bundesrechts 01.01.2019 SNSF Professorships

Abstract

The proposed project aims to develop methods for the automated detection of violations of linguistic guidelines in legislative drafts, and to implement and evaluate them in a prototypical tool. Its most important innovative contribution is the enhancement of the method of error modelling, which was developed for automated style checking in technical writing, to meet the requirements of legislative editing -- a domain largely out of reach for state-of-the-art style checkers.Error modelling means that texts are searched for specific features that indicate a potential styleguide violation. For two reasons, this task is more challenging in legislative drafts than it is in technical manuals. Firstly, legislative language is considerably more complex than technical language. Secondly, while linguistic guidelines for technical writing contain relatively simple typographical and grammatical rules (e.g. that measurement nouns should be abbreviated or that future tense should be avoided), a substantial number of legislative drafting rules are concerned with domain-specific discourse-related issues (e.g. that one sentence should not contain more than one norm or that legal definitions must not contain normative elements). Formulating detection strategies for violations of these latter type of guidelines is not trivial.We propose to tackle the problem by enhancing the method of error modelling with concepts from legal information retrieval. We plan to develop detection strategies that exploit and combine domain-specific information from multiple levels of analysis: layout information, document structure, conventionalised key phrases, morphological features and syntactic patterns.To provide proof of concept, we plan to implement a tool that automatically annotates legislative drafts with such mixed-level information and then searches them for combinations of features that indicate a potential violation of legislative drafting guidelines. Detected passages will be highlighted in the draft, and an appropriate help text will be made available to the user.The project focuses on German-language legislative drafting in Switzerland.
-