3,055 Hits in 7.6 sec

Deep Ensemble Learning for Legal Query Understanding

Arunprasath Shankar, Venkata Nagaraju Buddarapu
2018 International Conference on Information and Knowledge Management  
Legal query understanding is a complex problem that involves two natural language processing (NLP) tasks that needs to be solved together: (i) identifying intent of the user and (ii) recognizing entities  ...  accuracy and F-measure for legal intent classification and entity recognition.  ...  However, there is not much work done towards legal domain involving neither deep learning nor ensemble learning.  ... 
dblp:conf/cikm/ShankarB18 fatcat:wtjmt6ojwvh6jg7g7azeibfgqi

JNLP Team: Deep Learning for Legal Processing in COLIEE 2020 [article]

Ha-Thanh Nguyen, Hai-Yen Thi Vuong, Phuong Minh Nguyen, Binh Tran Dang, Quan Minh Bui, Sinh Trong Vu, Chau Minh Nguyen, Vu Tran, Ken Satoh, Minh Le Nguyen
2020 arXiv   pre-print
We propose deep learning based methods for automatic systems of legal retrieval and legal question-answering in COLIEE 2020.  ...  This approach helps to overcome the data scarcity and achieve good performance, thus can be useful for tackling related problems in information retrieval, and decision support in the legal domain.  ...  CONCLUSION In this paper, we reported our methods and results in using different techniques with Deep learning for the COLIEE 2020 comprehensive legal text processing tasks.  ... 
arXiv:2011.08071v1 fatcat:e7d6vmamhjbljolmv4a3zrs5ai

Transformer-Based Approaches for Legal Text Processing

Ha-Thanh Nguyen, Minh-Phuong Nguyen, Thi-Hai-Yen Vuong, Minh-Quan Bui, Minh-Chau Nguyen, Tran-Binh Dang, Vu Tran, Le-Minh Nguyen, Ken Satoh
2022 The Review of Socionetwork Strategies  
In this paper, we introduce our approaches using Transformer-based models for different problems of the COLIEE 2021 automatic legal text processing competition.  ...  We describe in detail the processing steps for each task such as problem formulation, data processing and augmentation, pretraining, finetuning.  ...  Legal documents are even hard for the lay reader to read. And our mission is to train a deep learning model, a machine to understand the text and give the correct answer.  ... 
doi:10.1007/s12626-022-00102-2 fatcat:mii4xqiksbgtppvfeebmirk6pm

Data Shift in Legal AI Systems

Venkata Nagaraju Buddarapu, Arunprasath Shankar
2019 International Conference on Artificial Intelligence and Law  
The motivation of this research is to study the effect of covariate shift on deep learning systems used in legal research.  ...  This shift in data is often responsible for the deterioration in predictive performance of machine learning systems.  ...  This research aims to observe, detect and adapt covariate shift on deep learning models using high-dimensional word embeddings, derived from a corpus of legal queries.  ... 
dblp:conf/icail/BuddarapuS19 fatcat:cdjbwzuxtvbedjyhpnb3rb3vbi

Semantic Data Ingestion for Intelligent, Value-Driven Big Data Analytics

Jeremy Debattista, Judie Attard, Rob Brennan
2018 2018 4th International Conference on Big Data Innovations and Applications (Innovate-Data)  
In this position paper we describe a conceptual model for intelligent Big Data analytics based on both semantic and machine learning AI techniques (called AI ensembles).  ...  creating AI ensembles.  ...  ACKNOWLEDGEMENT We would like to thank Giovanni Schiuma, Markus Helfurt, Pieter De Leenheer, Eamonn Clinton, Diego Calvanese, Christian Dirschl, Ismael Caballero, Hans Viehmann, and Rico Richter for their  ... 
doi:10.1109/innovate-data.2018.00008 dblp:conf/obd/DebattistaAB18 fatcat:3hiyg2rd4fh2hdx37jelozkz5e

International Workshop on Legal Data Analytics and Mining (LeDAM 2018): Preface to the Proceedings

Arindam Pal, Arnab Bhattacharya, Indrajit Bhattacharya, Kripabandhu Ghosh, Lipika Dey, Marie-Francine Moens, Saptarshi Ghosh
2018 International Conference on Information and Knowledge Management  
Data Mining, Information Retrieval, and Machine Learning communities.  ...  Legal data mining systems are important to provide easier access to and insights about law for both common persons and legal professionals.  ...  We are thankful to all the authors for submitting their papers to our workshop. We thank the PC members for carefully reviewing the papers.  ... 
dblp:conf/cikm/00010B0DMG18 fatcat:2nljfuvplfhuvhax6ascatvnfe

A Literature Review and Research Agenda on Explainable Artificial Intelligence (XAI)

Krishna Prakash Kalyanathaya, K. Krishna Prasad
2022 Zenodo  
Ensembles like Random Forest, Deep learning algorithms make the matter worst in terms of explaining the outcomes of decision even though these models produce more accurate results.  ...  Journals from multiple secondary data sources such as books and research papers published in various reputable publications which are relevant for the work were chosen in the methodology.  ...  Learning, Ensemble learning and Deep learning.  ... 
doi:10.5281/zenodo.5998487 fatcat:cyaqpxofivamrnzoe5bepe4m5m

Have You Stolen My Model? Evasion Attacks Against Deep Neural Network Watermarking Techniques [article]

Dorjan Hitaj, Luigi V. Mancini
2018 arXiv   pre-print
The increased cost of building a good deep neural network model gives rise to a need for protecting this investment from potential copyright infringements.  ...  Deep neural networks have had enormous impact on various domains of computer science, considerably outperforming previous state of the art machine learning techniques.  ...  ACKNOWLEDGMENTS The authors would like to thank Briland Hitaj for the valuable comments and discussions on this work.  ... 
arXiv:1809.00615v1 fatcat:6skk543x2jfftd3m66ofxdw7he

Toward Improving Attentive Neural Networks in Legal Text Processing [article]

Ha-Thanh Nguyen
2022 arXiv   pre-print
In recent years, thanks to breakthroughs in neural network techniques especially attentive deep learning models, natural language processing has made many impressive achievements.  ...  Language models tend to grow larger and larger, though, without expert knowledge, these models can still fail in domain adaptation, especially for specialized fields like law.  ...  Motivations 1.2.1 Factor Analysis for Deep Legal Systems The first motivation of this study is to understand the factors that influence a deep legal system and to propose appropriate improvements based  ... 
arXiv:2203.08244v1 fatcat:54rx64cucfdw3bzeujrmx5s7z4

Artificial Intelligence as Legal Research Assistant

Jhanvi Arora, Tanay Patankar, Alay Shah, Shubham Joshi
2020 Forum for Information Retrieval Evaluation  
In the first part of the paper, we have identified the relevant prior cases and statutes for the provided query using approaches based on BM 25, Topic embeddings and Law2Vec embeddings.  ...  For the second part, we used BERT to semantically segment a legal case document into Seven pre-defined labels or "rhetorical roles".  ...  Problem Definition Artificial Intelligence for Legal Assistance (AILA) was one of the tracks available for the Forum for Information Retrieval (FIRE) 2020 [1] .  ... 
dblp:conf/fire/AroraPSJ20 fatcat:fjzcag7wnrbhpbuonsxf6b7yra

Exploring complex and big data

Jerzy Stefanowski, Krzysztof Krawiec, Robert Wrembel
2017 International Journal of Applied Mathematics and Computer Science  
The links with related areas, including data streams and deep learning, are discussed. The common theme that naturally emerges from this characterization is complexity.  ...  This paper shows how big data analysis opens a range of research and technological problems and calls for new approaches.  ...  Also, deep learning is clearly not a panaceum to all big data challenges; for instance, deep learning models hardly ever provide for transparency and human-readable explanation.  ... 
doi:10.1515/amcs-2017-0046 fatcat:q6ugvobzi5cmbos4ct52mb3d34

Unsupervised law article mining based on deep pre-trained language representation models with application to the Italian civil code

Andrea Tagarelli, Andrea Simeri
2021 Artificial Intelligence and Law  
lack of test query benchmarks for Italian legal prediction tasks.  ...  Focusing on the law article retrieval task, we present a deep learning framework named LamBERTa, which is designed for civil-law codes, and specifically trained on the Italian civil code.  ...  .: BERT-based ensemble methods with data augmen- tation for legal textual entailment in COLIEE statute law task.  ... 
doi:10.1007/s10506-021-09301-8 fatcat:emqt5cqekffu5d6mttoljse5xm

A System Framework for Personalized and Transparent Data-Driven Decisions [chapter]

Sarah Oppold, Melanie Herschel
2020 Lecture Notes in Computer Science  
Our framework personalizes the choice of model for individuals or groups of users based on metadata about data sets and machine learning models.  ...  Querying and processing these metadata ensures transparency by supporting various kinds of queries by different stakeholders.  ...  ., in the data they are trained on or in the machine learning technique used (ranging from simple supervised learning to deep learning).  ... 
doi:10.1007/978-3-030-49435-3_10 fatcat:44jflubvfzf5xayn5e4trhotym

Overview of the FIRE 2019 AILA Track: Artificial Intelligence for Legal Assistance

Paheli Bhattacharya, Kripabandhu Ghosh, Saptarshi Ghosh, Arindam Pal, Parth Mehta, Arnab Bhattacharya, Prasenjit Majumder
2019 Forum for Information Retrieval Evaluation  
Given a situation that can lead to filing a case, the precedent retrieval task aims at finding case documents where similar legal situations were addressed.  ...  There were two tasks for this track: (i) Identifying relevant prior cases for a given situation (Precedent Retrieval), and (ii) Identifying most relevant statutes for a given situation (Statute Retrieval  ...  Acknowledgements: The track organizers thank all the participants for their interest in this track. We also thank the FIRE 2019 organizers for their support in organizing the track.  ... 
dblp:conf/fire/BhattacharyaG0019a fatcat:djuswzqn2bgmzaoc7vvzz43irq

Deep Learning Based Multi-Label Text Classification of UNGA Resolutions [article]

Francesco Sovrano, Monica Palmirani, Fabio Vitali
2020 arXiv   pre-print
Deep Learning (DL) is nowadays one of the most powerful tools for state-of-the-art (SOTA) AI for this task, but very often it comes with the cost of an expensive and error-prone preparation of a training-set  ...  learning or any other expensive training procedure.  ...  We designed a new ensemble method that effec-tively combines generic (non domain-specific) deep learning based document similarities with domain-specific TF-IDF document similarities, for achieving SDG  ... 
arXiv:2004.03455v1 fatcat:s3pk234qnffufcbd2z6sc5iawi
« Previous Showing results 1 — 15 out of 3,055 results