An information extraction framework for legal documents: A case study of Thai Supreme Court verdicts

Kowsrihawat, Kankawin; Vateekul, Peerapon

doi:10.1109/jcsse.2015.7219809

Cited by 11 publications

(6 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We can overcome this by either applying pattern-based techniques (using regular expressions) or semi-supervised learning techniques. Although pattern-based systems (Andrew, 2018;Cheng, Cua, Tan, Yao, & Roxas, 2009;Dozier et al, 2010;Kowsrihawat & Vateekul, 2015;Zhuang et al, 2017) are more appealing due to their performance, they demand deep domain-knowledge and often are too time-consuming and expensive. On the other hand, the semi-supervised learning approach (bootstrapping) is capable of extracting knowledge from a large set of unlabelled data using a list of seed examples or seed patterns.…”

Section: Why Judicial Domain?mentioning

confidence: 99%

“…Later, by using a probabilistic model, the key sentences were selected from each identified segment followed by composing them in the form of a headnote. Kowsrihawat and Vateekul (2015) developed a system called "JudgeDoll", which automatically extracted the gist and provided a legal summary of the full judgement which in turn helped the judge to rapidly summarize points of law with correct and reliable results. The experiment was conducted on the data set of Thai Supreme Court cases, particularly civil and criminal.…”

Section: Related Work On Judicial Iementioning

confidence: 99%

“…From the reviewed literature, we conclude that most research in the judicial domain is rule-based, knowledge-based, machine-learning based or by using pure linguistic techniques. Even though rule-based systems (Andrew (2018); Cheng et al (2009); Dozier et al (2010); Kowsrihawat and Vateekul (2015); Zhuang et al (2017)) are more appealing due to their performance, they demand deep domain-knowledge and a lot of manual work. Moreover, the maintenance of these systems often becomes too time-consuming and expensive.…”

Section: Related Work On Judicial Iementioning

confidence: 99%

See 2 more Smart Citations

Semi‐supervised, knowledge‐integrated pattern learning approach for fact extraction from judicial text

Thomas

Sangeetha

2021

Expert Systems

View full text Add to dashboard Cite

Tremendous growth in the availability of judicial documents has demanded the rise of information extraction (IE) techniques that support the automatic extraction of relevant concepts or data from judicial texts. Among various approaches available for IE, ontology‐based IE has proven to be the most appropriate for extracting domain‐specific information from natural language text. Through this article, we propose a knowledge‐driven, semi‐supervised pattern‐based learning (bootstrapping) approach to extract domain‐specific facts from judicial text, starting with a small set of seed facts. In the semantic analysis of legal text, fact extraction is the next step to entity identification, which involves the identification of roles played by each entity in the judicial text. The proposed methodology learns extraction patterns for 12 classes of facts from the judicial text through the integration of the domain ontology called judicial case ontology (JCO). The experimental results were evaluated by human judges and found to be quite promising. One main feature of the proposed methodology is its portability across various domains (such as medical, banking, insurance, etc.) which in turn helps build expert systems in various sectors.

show abstract

Section: Why Judicial Domain?mentioning

confidence: 99%

Section: Related Work On Judicial Iementioning

confidence: 99%

Section: Related Work On Judicial Iementioning

confidence: 99%

See 1 more Smart Citation

Semi‐supervised, knowledge‐integrated pattern learning approach for fact extraction from judicial text

Thomas

Sangeetha

2021

Expert Systems

View full text Add to dashboard Cite

show abstract

“…In Thailand, Civil Court Case Management System presented efficient service delivery to the stakeholders, through the availability of the case data digitally to the public and court users from the electronic registers and faster-searching functionality, with improving the security by implementing user groups and privileges (Rungruangpattana and Achalakul, 2008). To accelerate the judgment process, they implemented a so-called "JudgeDoll" to generate the final decision (Kowsrihawat and Vateekul, 2015). Chinese courts proposed an "intelligent court system" to allow remote connection for performing faster collaborative activities between different court institutions and results in "on-call" and "non-stop" judges with a transparent process (Xu, 2017).…”

Section: Related Workmentioning

confidence: 99%

Impact of e-court systems implementation: a case study

Ahmed

Muhammed

Pappel

et al. 2021

View full text Add to dashboard Cite

Purpose E-court systems automate court processes and provide better case administration with more effective and efficient justice delivery. This paper aims to present the e-court system in the Sulaimaniyah Appellate Court in the Kurdistan Region of Iraq as a case study. It identifies significant improvements after adopting the system. Design/methodology/approach This study used a qualitative approach with an exploratory case study design. Data collected from a triangulation of three sources through structured expert interviews with 30 stakeholders, personal observations by two of the authors, supported by analyzing current relevant literature. R package for Qualitative Data Analysis was the analysis tool. Findings Findings showed 10 improvements that enhanced court efficiency and effectiveness concerning better case administration, a more transparent process and increased court case security. Research limitations/implications This research is limited to improvements after adopting an e-court system. Practical implications This research provides a foundation for practitioners who are on the way to implement the e-court system and serves the decision-makers in the Kurdistan Regional Government to plan future expansion in the region. Originality/value This research focuses on the e-court system in the Kurdistan Region of Iraq. It is implemented as a first e-service to be a pilot for a broader plan to integrate all appellate courts in other cities in the Kurdistan of Iraq, hence, stepping toward the implementation of e-government.

show abstract

“…They extract predefined relations with hand-crafted patterns between named entities. The goal is different in the work of Kowsrihawat and Vateekul [29]. Their service called JudgeDoll extracts the main facts and summarizes Thai Supreme Court verdicts.…”

Section: Task 4 -Relation Extractionmentioning

confidence: 99%

A Survey of Thai Knowledge Extraction for the Semantic Web Research and Tools

Netisopakul

Wohlgenannt

2018

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

As the manual creation of domain models and also of linked data is very costly, the extraction of knowledge from structured and unstructured data has been one of the central research areas in the Semantic Web field in the last two decades. Here, we look specifically at the extraction of formalized knowledge from natural language text, which is the most abundant source of human knowledge available. There are many tools on hand for information and knowledge extraction for English natural language, for written Thai language the situation is different. The goal of this work is to assess the state-of-the-art of research on formal knowledge extraction specifically from Thai language text, and then give suggestions and practical research ideas on how to improve the state-of-the-art. To address the goal, first we distinguish nine knowledge extraction for the Semantic Web tasks defined in literature on knowledge extraction from English text, for example taxonomy extraction, relation extraction, or named entity recognition. For each of the nine tasks, we analyze the publications and tools available for Thai text in the form of a comprehensive literature survey. Additionally to our assessment, we measure the self-assessment by the Thai research community with the help of a questionnaire-based survey on each of the tasks. Furthermore, the structure and size of the Thai community is analyzed using complex literature database queries. Combining all the collected information we finally identify research gaps in knowledge extraction from Thai language. An extensive list of practical research ideas is presented, focusing on concrete suggestions for every knowledge extraction task -which can be implemented and evaluated with reasonable effort. Besides the task-specific hints for improvements of the state-of-the-art, we also include general recommendations on how to raise the efficiency of the respective research community. key words: knowledge extraction, Thai language text, landscape analysis, semantic web † †

show abstract

An information extraction framework for legal documents: A case study of Thai Supreme Court verdicts

Cited by 11 publications

References 4 publications

Semi‐supervised, knowledge‐integrated pattern learning approach for fact extraction from judicial text

Semi‐supervised, knowledge‐integrated pattern learning approach for fact extraction from judicial text

Impact of e-court systems implementation: a case study

A Survey of Thai Knowledge Extraction for the Semantic Web Research and Tools

Contact Info

Product

Resources

About