Towards an Automated Production of Legal Texts Using Recurrent Neural Networks

16th International Conference Artificial Intelligence and Law, Conference Proceedings, June 2017, pp. 229-332.

Ottawa Faculty of Law Working Paper No. 2017-27

5 Pages Posted: 18 Jun 2017 Last revised: 18 Jul 2017

Wolfgang Alschner

University of Ottawa - Common Law Section

Dmitriy Skougarevskiy

Graduate Institute of International and Development Studies (IHEID) - Department of Economics, Students; European University at St. Petersburg (EUSP)

Date Written: June 12, 2017

Abstract

This paper constructs a legal text generation and assembly system in the domain of international investment law. We rely on a corpus of 1600 bilateral investment treaties split into 22 600 articles to train a character-level recurrent neural network (char-RNN). Prior work has shown that while char-RNNs can produce legally meaningful texts, its output tends to be repetitive. In this contribution, we remedy this shortcoming by proposing a new framework for RNN-based text production. First, we elicit priors at the training stage to give more weight to under-represented treaty practice. Second, we use q-gram distance and GloVe word embeddings as filters imposed on the generated texts to draw them closer to a target document. Third, we develop a validation routine that compares the distribution of pre-defined legal concepts in actual and generated texts. Our results indicate that the RNN produces texts that are not repetitive and convey meaningful legal concepts. We conclude by showcasing a practical application of our framework by predicting provisions of the USA-China bilateral investment treaty currently under negotiation.

Keywords: recurrent neural network, artificial intelligence, law, document production, investment treaties, international law

Suggested Citation

Alschner, Wolfgang and Skougarevskiy, Dmitriy, Towards an Automated Production of Legal Texts Using Recurrent Neural Networks (June 12, 2017). 16th International Conference Artificial Intelligence and Law, Conference Proceedings, June 2017, pp. 229-332.; Ottawa Faculty of Law Working Paper No. 2017-27. Available at SSRN: https://ssrn.com/abstract=2984920

Wolfgang Alschner (Contact Author)

University of Ottawa - Common Law Section ( email )

57 Louis Pasteur Street
Ottawa, K1N 6N5
Canada

Dmitriy Skougarevskiy

Graduate Institute of International and Development Studies (IHEID) - Department of Economics, Students ( email )

Geneva
Switzerland

HOME PAGE: http://graduateinstitute.ch/economics

European University at St. Petersburg (EUSP) ( email )

3 Gagarinskaya Street
St. Petersburg, 191187
Russia

HOME PAGE: http://eu.spb.ru

Paper statistics

Downloads
40
Abstract Views
157