Atefeh Farzindar

Supervised machine learning for summarizing legal documents

This paper presents a supervised machine learning approach for summarizing legal documents A commercial system for the analysis and summarization of legal documents provided us with a corpus of almost 4,000 text and extract pairs for our machine learning experiments That corpus was pre-processed to identify the selected source sentences in extracts from which we generated legal structured data We finally describe our sentence classification experiments relying on a Naive Bayes classifier using a set of surface, emphasis, and content features.

An automatic system for summarization and information extraction of legal information

This paper presents an information system for legal professionals that integrates natural language processing technologies such as text classification and summarization. We describe our experience in the use of a mix of linguistics aware transductor and XML technologies for bilingual information extraction from judgements in both French and English within a legal information and summarizing system. We present the context of the work, the main challenges and how they were tackled by clearly separating language and domain dependent terms and vocabularies. After having been developed on the immigration law domain, the system was easily ported to the intellectual property and tax law domains.

Machine Translation of Legal Information and Its Evaluation

This paper presents the machine translation system known as TransLI (Translation of Legal Information) developed by the authors for automatic translation of Canadian Court judgments from English to French and from French to English. Normally, a certified translation of a legal judgment takes several months to complete. The authors attempted to shorten this time significantly using a unique statistical machine translation system which has attracted the attention of the federal courts in Canada for its accuracy and speed. This paper also describes the results of a human evaluation of the output of the system in the context of a pilot project in collaboration with the federal courts of Canada.

Domain adaptation techniques for machine translation and their evaluation in a real-world setting

Statistical Machine Translation (SMT) is currently used in real-time and commercial settings to quickly produce initial translations for a document which can later be edited by a human. The SMT models specialized for one domain often perform poorly when applied to other domains. The typical assumption that both training and testing data are drawn from the same distribution no longer applies. This paper evaluates domain adaptation techniques for SMT systems in the context of end-user feedback in a real world application. We present our experiments using two adaptive techniques, one relying on log-linear models and the other using mixture models. We describe our experimental results on legal and government data, and present the human evaluation effort for post-editing in addition to traditional automated scoring techniques (BLEU scores). The human effort is based primarily on the amount of time and number of edits required by a professional post-editor to improve the quality of machine-generated translations to meet industry standards. The experimental results in this paper show that the domain adaptation techniques can yield a significant increase in BLEU score (up to four points) and a significant reduction in post-editing time of about one second per word.