Filters








100,874 Hits in 3.7 sec

An Evaluation Dataset for Legal Word Embedding: A Case Study On Chinese Codex [article]

Chun-Hsien Lin, Pu-Jen Cheng
2022 arXiv   pre-print
Word embedding is a modern distributed word representations approach widely used in many natural language processing tasks.  ...  Moreover, we discovered that legal relations might be ubiquitous in the word embedding model.  ...  Then, TensorBoard is used to visually assist manual inspection of the relevance of each word in the vector space.  ... 
arXiv:2203.15173v1 fatcat:ayeb3ivnzbentmsqs67eekwboa

Automatic Taxonomy Generation - A Use-Case in the Legal Domain [article]

Cécile Robin, James O'Neill, Paul Buitelaar
2017 arXiv   pre-print
A key challenge in the legal domain is the adaptation and representation of the legal knowledge expressed through texts, in order for legal practitioners and researchers to access this information easier  ...  One way to approach this goal is in the form of a taxonomy of legal concepts.  ...  The embedded dimensions are reduced representations of the words in an embedding space.  ... 
arXiv:1710.01823v1 fatcat:7dfarvnh7bdxvbqmobfx3npk34

Accounting for Sentence Position and Legal Domain Sentence Embedding in Learning to Classify Case Sentences [chapter]

Huihui Xu, Jaromir Savelka, Kevin D. Ashley
2021 Frontiers in Artificial Intelligence and Applications  
We also compare the legal domain specific sentence embedding with other general purpose sentence embeddings to gauge the effect of legal domain knowledge, captured during pre-training, on text classification  ...  We also verified that legal domain specific sentence embeddings perform better, and that meta-sentence embedding can further enhance performance when sentence position information is included.  ...  Researchers in [4] used three types of autoencoders to meta-embeddings of words. milarly, sentence embedding is the dense vector representation of a sentence.  ... 
doi:10.3233/faia210314 fatcat:b573ndi7x5hj3icyrouas4s2au

Sentence Embeddings and High-Speed Similarity Search for Fast Computer Assisted Annotation of Legal Documents [chapter]

Hannes Westermann, Jaromír Šavelka, Vern R. Walker, Kevin D. Ashley, Karim Benyekhlef
2020 Frontiers in Artificial Intelligence and Applications  
Human-performed annotation of sentences in legal documents is an important prerequisite to many machine learning based systems supporting legal tasks.  ...  We use this observation in allowing annotators to quickly view and annotate sentences that are semantically similar to a given sentence, across an entire corpus of documents.  ...  More recently, pre-trained word embeddings and language models have gained popularity in creating word embeddings.  ... 
doi:10.3233/faia200860 fatcat:krtl5brwsvdrfmrmvmwd6f4en4

Neural Embeddings for the Elicitation of Jurisprudence Principles: The Case of Arabic Legal Texts

Nafla Alrumayyan, Maha Al-Yahya
2022 Applied Sciences  
We investigated neural embeddings—specifically, doc2vec architectures—as a representation model for the task of JP elicitation using Arabic legal texts.  ...  In addition, we explored an approach that integrates task-oriented word embeddings (ToWE) with document embeddings (paragraph vectors).  ...  The proposed model empowered by an Arabic domain ontology assists in extracting legal terms from related documents.  ... 
doi:10.3390/app12094188 fatcat:o45fnnez7jhftmwidlsk32nfhu

A Corpus Approach to Roman Law Based on Justinian's Digest

Marton Ribary, Barbara McGillivray
2020 Informatics  
By building and comparing Latin word embeddings models, we were also able to detect a semantic split in words with general and legal sense.  ...  The paper presents a series of computer-assisted methods to open new frontiers of inquiry.  ...  We used the words included in the general and legal benchmarks to compare the word embeddings models in more detail.  ... 
doi:10.3390/informatics7040044 fatcat:pcjk2ahgxna7zfa64hmtmerabi

An Artificial Intelligence based Analysis in Legal domain

2019 VOLUME-8 ISSUE-10, AUGUST 2019, REGULAR ISSUE  
In this study, we review about the different methods of deep learning used in legal tasks such as Legal data search, Legal document analytics, and Legal perspective interface.  ...  To solve aggregate tasks, one can use the deep learning methods like, Recurrent Network Networks (RNN), Gated Recurrent unit network (GRU), Long Short Term Memory networks (LSTM), Convolutional neural  ...  Train the legal word embeddings using word2vec technique. 2. Select the CNN classifiers for document summarization.  ... 
doi:10.35940/ijitee.b1113.1292s219 fatcat:nk4nnpe4urgsbmowwfeysfgtke

Empirical Study of Deep Learning for Text Classification in Legal Document Review

Fusheng Wei, Han Qin, Shi Ye, Haozhen Zhao
2018 2018 IEEE International Conference on Big Data (Big Data)  
This paper reports our preliminary studies in using deep learning in legal document review.  ...  Specifically, we conducted experiments to compare deep learning results with results obtained using a SVM algorithm on the four datasets of real legal matters.  ...  coding or technology assisted review (TAR) in the legal domain.  ... 
doi:10.1109/bigdata.2018.8622157 dblp:conf/bigdataconf/WeiQYZ18 fatcat:wgipm2g5ubbgflergi5gaelt7q

Learning to Predict Charges for Criminal Cases with Legal Basis

Bingfeng Luo, Yansong Feng, Jianbo Xu, Xiang Zhang, Dongyan Zhao
2017 Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing  
The charge prediction task is to determine appropriate charges for a given case, which is helpful for legal assistant systems where the user input is fact description.  ...  The experimental results show that, besides providing legal basis, the relevant articles can also clearly improve the charge prediction results, and our full model can effectively predict appropriate charges  ...  Such techniques are crucial for legal assistant systems, where users could find similar cases or possible penalties by describing a case with their own words.  ... 
doi:10.18653/v1/d17-1289 dblp:conf/emnlp/LuoFXZZ17 fatcat:gbabcmc3ancs7kimymhp75dzti

Recognition of Chinese Legal Elements Based on Transfer Learning and Semantic Relevance

Dian Zhang, Hewei Zhang, Long Wang, Jiamei Cui, Wen Zheng, Yan Huang
2022 Wireless Communications and Mobile Computing  
In recent years, LegalAI has rapidly attracted the attention of AI researchers and legal professionals alike. Elements of LegalAI are known as legal elements.  ...  This research method makes full use of the semantic information of text, which is essential in the judicial field of document processing.  ...  The positional embedding in BERT uses the learned positional embedding; this is done using the function used to compute the positional encoding in the transformer.  ... 
doi:10.1155/2022/1783260 fatcat:dg75q5o33vbjdde6bp5pszqbga

Gender and Racial Stereotype Detection in Legal Opinion Word Embeddings [article]

Sean Matthews, John Hudzina, Dawn Sepehr
2022 arXiv   pre-print
Our analyses using these methods suggest that racial and gender biases are encoded into word embeddings trained on legal opinions.  ...  We first explain how previously proposed methods for identifying these biases are not well suited for use with word embeddings trained on legal opinion text.  ...  Contributions As discussed previously, word embeddings are used in many practical NLP systems which operate on legal language.  ... 
arXiv:2203.13369v2 fatcat:3wix7va6ybbo5kpfa2tnwxcqce

Stop Illegal Comments: A Multi-Task Deep Learning Approach [article]

Ahmed Elnaggar, Bernhard Waltl, Ingo Glaser, Jörg Landthaler, Elena Scepankova, Florian Matthes
2018 arXiv   pre-print
Deep learning methods are often difficult to apply in the legal domain due to the large amount of labeled data required by deep learning methods.  ...  These powerful novel models are capable of transferring knowledge among different tasks or training sets and therefore could open up the legal domain for many deep learning applications.  ...  Acknowledgements We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan XP Pascal GPU used for this research.  ... 
arXiv:1810.06665v1 fatcat:noppt5upurbjpoipjh5id7yrji

Text-mining for Lawyers: How Machine Learning Techniques Can Advance our Understanding of Legal Discourse

Arthur Dyevre
2021 Erasmus Law Review  
BERT models pre-trained on large collections of legal documents have also been released to assist with legal classification and prediction tasks.  ...  While the study of legal texts is at least as old as academic legal scholarship, what is new is that a whole range of text mining techniques have emerged to assist the legal community in navigating and  ...  Word size is determined by the maximum deviation .  ... 
doi:10.5553/elr.000191 fatcat:bcwpxq6dlzffjb42uwwl764ufi

Analysing Predictive Coding Algorithms for Document Review

Aditi Wikhe
2021 International Journal for Research in Applied Science and Engineering Technology  
Deep learning models mixed with word embeddings have demonstrated to be more effective in predictive coding in recent years.  ...  In the legal domain, text classification is referred to as predictive coding or technology assisted review (TAR).  ...  In order to compare, we undertake the following experiments: (1) fine-tuned pre-trained word embeddings, no pre trained word embeddings, and static pre-trained word embeddings; (2) different kernel sizes  ... 
doi:10.22214/ijraset.2021.39076 fatcat:3yfyleh6trehjpfo3nakvn7sq4

Brazilian Court Documents Clustered by Similarity Together Using Natural Language Processing Approaches with Transformers [article]

Raphael Souza de Oliveira, Erick Giovani Sperandio Nascimento
2022 arXiv   pre-print
210,000 legal proceedings.  ...  Documents were pre-processed and had their content transformed into a vector representation using these NLP techniques.  ...  embeddings in Portuguese (pt-BR) achieved superior results when compared to the specialized legal corpus word embeddings.  ... 
arXiv:2204.07182v2 fatcat:5elyrgitnnggdn72ydr3uqt4iu
« Previous Showing results 1 — 15 out of 100,874 results