Information Extraction with Active Learning: A Case Study in Legal Text

Cardellino, Cristian; Villata, Serena; Alemany, Laura Alonso; Cabrio, Elena

doi:10.1007/978-3-319-18117-2_36

Cited by 9 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Active learning is particularly useful when the unlabeled data samples are abundant, whereas manually labelling all of them is expensive or infeasible. Active learning is widely used in many areas, such as text classification [18], information extraction [9], image classification [21], and speech recognition [30].…”

Section: Active Learningmentioning

confidence: 99%

EvoCLINICAL: Evolving Cyber-Cyber Digital Twin with Active Transfer Learning for Automated Cancer Registry System

Lu,

Xu,

Yue

et al. 2023

Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Enginee

View full text Add to dashboard Cite

The Cancer Registry of Norway (CRN) collects information on cancer patients by receiving cancer messages from different medical entities (e.g., medical labs, hospitals) in Norway. Such messages are validated by an automated cancer registry system: GURI. Its correct operation is crucial since it lays the foundation for cancer research and provides critical cancer-related statistics to its stakeholders. Constructing a cyber-cyber digital twin (CCDT) for GURI can facilitate various experiments and advanced analyses of the operational state of GURI without requiring intensive interactions with the real system. However, GURI constantly evolves due to novel medical diagnostics and treatment, technological advances, etc. Accordingly, CCDT should evolve as well to synchronize with GURI. A key challenge of achieving such synchronization is that evolving CCDT needs abundant data labelled by the new GURI.To tackle this challenge, we propose EvoCLINICAL, which considers the CCDT developed for the previous version of GURI as the pretrained model and fine-tunes it with the dataset labelled by querying a new GURI version. EvoCLINICAL employs a genetic algorithm to select an optimal subset of cancer messages from a candidate dataset and query GURI with it. We evaluate EvoCLIN-ICAL on three evolution processes. The precision, recall, and F1 score are all greater than 91%, demonstrating the effectiveness of EvoCLINICAL. Furthermore, we replace the active learning part of EvoCLINICAL with random selection to study the contribution of transfer learning to the overall performance of EvoCLINICAL. Results show that employing active learning in EvoCLINICAL increases its performance consistently.

show abstract

Section: Active Learningmentioning

confidence: 99%

EvoCLINICAL: Evolving Cyber-Cyber Digital Twin with Active Transfer Learning for Automated Cancer Registry System

Lu,

Xu,

Yue

et al. 2023

Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Enginee

View full text Add to dashboard Cite

show abstract

“…Active learning has also been used in information extraction (Culotta, Kristjansson, McCallum, & Viola, 2006;Finn & Kushmerick, 2003;Jones, Ghani, Mitchell, & Riloff, 2003;Scheffer, Decomain, & Wrobel, 2001) and word sense disambiguation (Chan & Ng, 2007;Chen, Schein, Ungar, & Palmer, 2006;Zhu & Hovy, 2007;Zhu, Wang, & Hovy, 2008). Olsson tified as most beneficial for the classification algorithm-for example, see Cardellino et al (2015) and Holzinger (2016) for further discussion on machine learning with oracle-in-the-loop or human in-the-loop. An important characteristic of active learning in text categorization is that it can reduce the human effort in text labelling by developing effective querying strategies.…”

Section: Active Learningmentioning

confidence: 99%

Using long short‐term memory neural networks to analyze SEC 13D filings: A recipe for human and machine interaction

Aydoğdu

Saraoglu

Louton

2019

Intell Sys Acc Fin Mgmt

View full text Add to dashboard Cite

Summary We implement an efficient methodology for extracting themes from Securities Exchange Commission 13D filings using aspects of human‐assisted active learning and long short‐term memory (LSTM) neural networks. Sentences from the ‘Purpose of Transaction’ section of each filing are extracted and a randomly chosen subset is labelled based on six filing themes that the existing literature on shareholder activism has shown to have an impact on stock returns. We find that an LSTM neural network that accepts sentences as input performs significantly better, with precision of 77%, than an alternately specified neural network that uses the common bag of words approach. This indicates that both sentence structure and vocabulary are important in classifying SEC 13D filings. Our study has important implications, as it addresses the recent cautions raised in the literature that analysis of finance and accounting‐related text sources should move beyond bag‐of‐words approaches to alternatives that incorporate the analysis of word sense and meaning reflecting context.

show abstract

“…If there is an approach to automatically extract key events from the materials of cases accurately, both labor and time costs would be reduced. It would also benefit further works if we store both the structured information and original materials in the database (Cardellino et al, 2015; Hao et al, 1996).…”

Section: Introductionmentioning

confidence: 99%

Judicial intelligent assistant system: Extracting events from Chinese divorce cases to detect disputes for the judge

Zhang,

Li,

Sheng

et al. 2024

Expert Systems

View full text Add to dashboard Cite

In the formal procedure of Chinese civil cases, the textual materials provided by different parties describe the development process of the cases. It is a difficult but necessary task to extract the key information for the cases from these textual materials and to clarify the dispute focus of related parties. Currently, officers read the materials manually and use methods, such as keyword searching and regular matching, to get the target information. These approaches are time‐consuming and heavily depend on prior knowledge and the carefulness of the officers. To assist the officers in enhancing working efficiency and accuracy, we conduct a case study of detecting disputes from Chinese divorce cases based on proposing a Two‐Round‐Labeling (TRL) event extracting technique in this article. We implement the Judicial Intelligent Assistant (JIA) system according to the proposed approach to (1) automatically extract focus events from divorce case materials, (2) align events by identifying co‐reference among them, and (3) detect conflicts among events brought by the plaintiff and the defendant. With the JIA system, it is convenient for judges to determine the disputed issues in Chinese divorce cases. Experimental results demonstrate that the proposed approach and system can obtain the focus of Chinese divorce cases and detect conflicts more effectively and efficiently compared with the existing method.

show abstract

Information Extraction with Active Learning: A Case Study in Legal Text

Cited by 9 publications

References 11 publications

EvoCLINICAL: Evolving Cyber-Cyber Digital Twin with Active Transfer Learning for Automated Cancer Registry System

EvoCLINICAL: Evolving Cyber-Cyber Digital Twin with Active Transfer Learning for Automated Cancer Registry System

Using long short‐term memory neural networks to analyze SEC 13D filings: A recipe for human and machine interaction

Judicial intelligent assistant system: Extracting events from Chinese divorce cases to detect disputes for the judge

Contact Info

Product

Resources

About