964 Hits in 4.3 sec

Easing Legal News Monitoring with Learning to Rank and BERT [chapter]

Luis Sanchez, Jiyin He, Jarana Manotumruksa, Dyaa Albakour, Miguel Martinez, Aldo Lipani
2020 Lecture Notes in Computer Science  
In this paper we present a legal search problem where professionals monitor news articles with constant queries on a periodic basis.  ...  In an attempt to capture the complex information needs of users, a learning to rank approach is adopted with user specified relevance criteria as features.  ...  The users monitor a specific legal topic by querying the news stream with that topic periodically and all the retrieved results are tagged with a relevance judgment for later usage.  ... 
doi:10.1007/978-3-030-45442-5_42 fatcat:5ekyep5gh5fi3gtr47vrk3hlie

Discovering Explanatory Sentences in Legal Case Decisions Using Pre-trained Language Models [article]

Jaromir Savelka, Kevin D. Ashley
2021 arXiv   pre-print
We show that the transformer-based models are capable of learning surprisingly sophisticated features and outperform the prior approaches to the task.  ...  We assembled a data set of 26,959 sentences, coming from legal case decisions, and labeled them in terms of their usefulness for explaining selected legal concepts.  ...  ple applications of bert for ad hoc document re- Easing legal news monitoring with learning to rank trieval. arXiv preprint arXiv:1903.10972. and bert.  ... 
arXiv:2112.07165v1 fatcat:dpua7bvionfjrgi74zbdboxzca

FedMatch: Federated Learning Over Heterogeneous Question Answering Data [article]

Jiangui Chen, Ruqing Zhang, Jiafeng Guo, Yixing Fan, Xueqi Cheng
2021 arXiv   pre-print
A possible solution to this dilemma is a new approach known as federated learning, which is a privacy-preserving machine learning technique over distributed datasets.  ...  Here the heterogeneity refers to the fact that annotated QA data are typically with non-identical and independent distribution (non-IID) and unbalanced sizes in practice.  ...  And then the authors recruit seven experts with legal training to construct answers to questions. Table 1 shows the overall statistics of our FedQA benchmark dataset.  ... 
arXiv:2108.05069v1 fatcat:myyo7g4dszcmlfx2pfsljxu7du

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  
To our knowledge, this is the first study proposing an advanced approach to law article prediction for the Italian legal system based on a BERT (Bidirectional Encoder Representations from Transformers)  ...  One key aspect of our LamBERTa framework is that we conceived it to address an extreme classification scenario, which is characterized by a high number of classes, the few-shot learning problem, and the  ...  Sanchez, L., He, J., Manotumruksa, J., Albakour, D., Martinez, M., Lipani, A.: Easing legal news monitoring with learning to rank and BERT. In: Proc. ECIR.  ... 
doi:10.1007/s10506-021-09301-8 fatcat:emqt5cqekffu5d6mttoljse5xm

Learning Representations and Agents for Information Retrieval [article]

Rodrigo Nogueira
2019 arXiv   pre-print
This agent can leverage the effort that has been put into designing and running efficient storage and retrieval systems by learning how to best utilize them to accomplish a task. ...  ...  This progress can be partially attributed to the recent success of machine learning and to the efficient methods for storing and retrieving information, most notably through web search engines.  ...  BM25 + Doc2query + BERT: We expand, index, and retrieve documents as in BM25 + Doc2query and further re-rank the documents with BERT.  ... 
arXiv:1908.06132v1 fatcat:xcujtsvsd5clljkteu4zrmr4hy

Managing International Branch Campuses: What Do We Know?

Nigel Healey
2015 Higher Education Quarterly  
International branch campuses: the current landscape The two main organisations which monitor the growth of IBCs globally are the OBHE and C-BERT.  ...  A closer look at the 200 or so international branch campuses being monitored by the OBHE and C-BERT reveals that, as Lane and Kinser (2012) observed, getting a clear definition 'is a fairly slippery  ... 
doi:10.1111/hequ.12082 fatcat:6vuzjllltfd3dc4esvqj6krx6y

Document Automation Architectures and Technologies: A Survey [article]

Mohammad Ahmadi Achachlouei, Omkar Patil, Tarun Joshi, Vijayan N. Nair
2021 arXiv   pre-print
academic research, and provides ideas that can lead to new research opportunities within the DA field in light of recent advances in artificial intelligence and deep neural networks.  ...  There have been reviews of commercial solutions of DA, particularly in the legal domain, but to date there has been no comprehensive review of the academic research on DA architectures and technologies  ...  Unsupervised and supervised ranking approaches are proposed where the potential candidate paragraphs are ranked according to their likeness of being associated with a requirement.  ... 
arXiv:2109.11603v1 fatcat:alqvdban5ndr7m3gjjtqqumk7y

On the Opportunities and Risks of Foundation Models [article]

Rishi Bommasani, Drew A. Hudson, Ehsan Adeli, Russ Altman, Simran Arora, Sydney von Arx, Michael S. Bernstein, Jeannette Bohg, Antoine Bosselut, Emma Brunskill, Erik Brynjolfsson, Shyamal Buch (+102 others)
2021 arXiv   pre-print
AI is undergoing a paradigm shift with the rise of models (e.g., BERT, DALL-E, GPT-3) that are trained on broad data at scale and are adaptable to a wide range of downstream tasks.  ...  Though foundation models are based on standard deep learning and transfer learning, their scale results in new emergent capabilities,and their effectiveness across so many tasks incentivizes homogenization  ...  In addition, we would like to especially thank Vanessa Parli for helping to organize this effort.  ... 
arXiv:2108.07258v2 fatcat:yktkv4diyrgzzfzqlpvaiabc2m

DeepHelp: Deep Learning for Shout Crisis Text Conversations [article]

Daniel Cahn
2021 arXiv   pre-print
To these ends, contributions to deep learning include a modified Transformer-over-BERT model; a framework for multitask learning to improve generalisation in the presence of sparse labels; and a mathematical  ...  Key results include a deep learning model with likely better performance at predicting suicide risk than trained CVs and the ability to predict whether a texter is 21 or under with 88.4% accuracy.  ...  Acknowledgements Thank you to Dr. Mark Ungless, Dr.  ... 
arXiv:2110.13244v1 fatcat:ka2hq4u7w5de7am666mmkyxgia

Design and empirical evaluation of search software for legal professionals on the WWW

Bert J Dempsey, Robert C Vreeland, Robert G Sumner, Kiduk Yang
2000 Information Processing & Management  
A directory services tool, LIBClient, provides a hierarchical index of legal information resources in an interface emphasizing ease-of-use by Internet novices and management of multiple-site searching.  ...  In conclusion, our research points to the promise of WWW search tool designs that tightly couple directed browsing with query-based Information Processing and Management 36 (2000) 253±273  ...  Also, many legal professionals are relatively new to the Internet and require tools with low complexity.  ... 
doi:10.1016/s0306-4573(99)00057-6 fatcat:v4b3xow6e5hz3hmvh3wmmt47zi

The use of information from the environment in the strategic decision-making process of Brazilian and American business owners of small business

Patricia Viveiros de Castro Krakauer, Martinho Isnard Ribeiro de Almeida
2016 Base  
ABSTRACT This study aims to understand the practices of Brazilian and American small and medium enterprises with regard to the use of environmental information in the strategic decision-making process.  ...  Some differences were noticed between Brazilian and American practices: the use of intuition, the sharing with family members and the dissemination of environmental information among team members.  ...  and learning.  ... 
doi:10.4013/base.2016.132.02 fatcat:3qlrsm4bgneutkagzqttj7qqhu

PolicyCLOUD: A prototype of a Cloud Serverless Ecosystem for Policy Analytics [article]

Ofer Biran, Oshrit Feder, Yosef Moatti, Athanasios Kiourtis, Dimosthenis Kyriazis, George Manias, Argyro Mavrogiorgou, Nikitas M. Sgouros, Martim Taborda Barata, Isabella Oldani, María Angeles Sanguino, Pavlos Kranas
2022 arXiv   pre-print
We demonstrate this with a Social Analytics tool implemented in conjunction with PolicyCLOUD and show how to benefit from policy modeling, design and simulation capabilities.  ...  Furthermore, PolicyCLOUD has developed a first of its kind legal and ethical framework that covers the usage and dissemination of datasets and analytic functions throughout its policy-relevant dataflows  ...  The authors are grateful to the rest of the PolicyCLOUD crew for their cooperation and support. Funding statement. "The research leading to the results presented in this article received funding from  ... 
arXiv:2201.06077v1 fatcat:crefonoz5rh6vpsclik7drhv3q

Understanding Smart Contracts: Hype or Hope? [article]

Elizaveta Zinovyeva, Raphael C. G. Reule, Wolfgang Karl Härdle
2021 arXiv   pre-print
Introduced in the early 1990s, the technology has gained a lot of attention with its application to blockchain technology to an extent, that can be considered a veritable hype.  ...  Reflecting the growing institutional interest, this intertwined exploratory study between statistics, information technology, and law contrasts these idealistic stories with the data reality and provides  ...  Interestingly, even BERT that is seen as a deep learning model that is able to deal with small datasets shows a very poor performance.  ... 
arXiv:2103.08447v1 fatcat:jmek7zk54rcuzb2uciocz4jb3q

Leading the White-Collar Union: Clive Jenkins, the Management of Trade-Union Officers, and the Politics of the British Labour Movement, c.19681979

Joseph Melling
2004 International Review of Social History  
of struggles between the union and its bargainers during the 1970s.  ...  It is argued that the strategies pursued by Jenkins, including the recruitment, training, and deployment of fieldworkers, were guided by accumulated knowledge and culture (as well as brilliant opportunism  ...  of the new recruits was not shared throughout the officer ranks.  ... 
doi:10.1017/s0020859003001378 fatcat:xnmco67rz5gv3fzwfmqb622mhi

A framework for fostering transparency in shared artificial intelligence models by increasing visibility of contributions

Iain Barclay, Harrison Taylor, Alun Preece, Ian Taylor, Dinesh Verma, Geeth Mel
2020 Concurrency and Computation  
documentation and improving transparency in machine learning assets shared within scientific communities.  ...  This paper presents a novel method for deriving a quantifiable metric capable of ranking the overall transparency of the process pipelines used to generate AI systems, such that users, auditors and other  ...  The U.S. and UK Governments are authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright notation hereon.  ... 
doi:10.1002/cpe.6129 fatcat:vbwhpy4icnhfvnwzfaezfses2m
« Previous Showing results 1 — 15 out of 964 results