Track website : https://sites.google.com/view/fire-2019-aila/
Conference website : http://fire.irsi.res.in/fire/2019/home
In countries following the Common Law system (e.g. UK, USA, Canada, Australia, India), there are two primary sources of law – Statutes and Precedents. Statutes are the prior cases decided in courts of law while Precedents are established laws, such as the Constitution of a country.
-
Statutes deal with applying legal principles to a situation (facts /scenario / circumstances which lead to filing the case).
-
Precedents or prior cases help a lawyer understand how the Court has dealt with similar scenarios in the past, and prepare the legal reasoning accordingly.
When a lawyer is presented with a situation (that will potentially lead to filing of a case), it will be very beneficial to one if there is an automatic system that identifies a set of related prior cases involving similar situations as well as statutes/acts that can be most suited to the purpose in the given situation.
Such a system shall not only help a lawyer but also benefit a common man, in a way of getting a preliminary understanding of the legal aspects pertaining to a situation, even before one approaches a lawyer. The system can assist one in identifying where one's legal problem fits, what legal actions one can proceed with (through statutes) and what were the outcomes of similar cases (through precedents).
Motivated by the above scenario, the FIRE 2019 track on ‘Artificial Intelligence for Legal Assistance’ (AILA) proposed two tasks:
- Identifying relevant prior cases for a given situation (Precedent Retrieval)
- Identifying most relevant statutes for a given situation (Statute Retrieval).
Domain : This is a task in the domain of Natural Language Processing, Information Retrieval and Data Mining.
Paper : This paper provides an overview of the FIRE 2019 AILA Track.
This repository contains python implimentations of the various methods described in the paper which include the following main techniques:
- Cosine Similarity
- Jaccard Similarity
- Doc2Vec
- BM 25
- Tf-Idf
- textRank
- Word2Vec Embeddings
- Word2Vec + Glove Vectors
- FastText
- Sent2Vec
- Bigram / Unigram model + linear Interpolation
- BERT
- IFB2 Weighting Model
- LexPageRank algorithm
used in conjunction with other mechanisms.
Citations and references: