Reference : An approach to information retrieval and question answering in the legal domain
Scientific congresses, symposiums and conference proceedings : Unpublished conference
Engineering, computing & technology : Multidisciplinary, general & others
Law / European Law
http://hdl.handle.net/10993/29385
An approach to information retrieval and question answering in the legal domain
English
Adebayo, Kolawole John[University of Luxembourg > Faculty of Science, Technology and Communication (FSTC) > Computer Science and Communications Research Unit (CSC) >]
Di Caro, Luigi[Università degli Studi di Torino - Unito > Dipartimento di Informatica > > Assistant Professor]
Boella, Guido[Università degli Studi di Torino - Unito > Dipartimento di Informatica > > Full Professor]
Bartolini, Cesare[University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > >]
15-Nov-2016
14
Yes
No
International
Proceedings of the Tenth International Workshop on Juris-informatics (JURISIN)
from 14-11-2016 to 15-11-2016
Kanagawa
Japan
[en] Child-Sum Tree LSTM ; Information Retrieval ; Textual entailment
[en] We describe in this paper, a report of our participation at COLIEE 2016 Information Retrieval (IR) and Legal Question Answering (LQA) tasks. Our solution for the IR part employs the use of a simple but effective Machine Learning (ML) procedure. Our Question Answering solution answers "YES or 'NO' to a question, i.e., 'YES' if the question is entailed by a text and 'NO' otherwise. With recent exploit of Multi-layered Neural Network systems at language modeling tasks, we presented a Deep Learning approach which uses an adaptive variant of the Long-Short Term Memory (LSTM), i.e. the Child Sum Tree LSTM (CST-LSTM) algorithm that we modified to suit our purpose. Additionally, we benchmarked this approach by handcrafting features for two popular ML algorithms, i.e., the Support Vector Machine (SVM) and the Random Forest (RF) algorithms. Even though we used some features that have performed well from similar works, we also introduced some semantic features for performance improvement. We used the results from these two algorithms as the baseline for our CST-LSTM algorithm. All evaluation was done on the COLIEE 2015 training and test sets. The overall result conforms the competitiveness of our approach.