Named Entity Recognition in Turkish Bank Documents

Kabasakal, Osman; Mutlu, Alev

doi:10.34088/kojose.871873

Cited by 2 publications

(2 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Surprisingly, topic-based KE tools like TopicRank and MultipartiteRank, where topics are viewed as nodes in a graph, do well on datasets with both short and long texts. Moreover, KE tools that incorporate word position as a feature, such as PositionRank, TextRank, and YAKE, tend to yield suboptimal results when applied to datasets where keywords are not evenly distributed throughout the text [76].…”

Section: ) Data Typementioning

confidence: 99%

A Comparative Assessment of Unsupervised Keyword Extraction Tools

Nadim,

Akopian,

Matamoros

2023

IEEE Access

View full text Add to dashboard Cite

The extraction of keywords is a critical task in natural language processing and information retrieval. It has become increasingly important in a wide range of applications, from search engines and ecommerce platforms to news and social media analysis. However, the evaluation of keyword extraction methods remains a challenging task due to the diverse range of data types and contexts used, as well as the complexity of the methodologies and techniques involved. In this regard, this study reviews the prior surveys on keyword extraction methods to comprehend the fundamental principles, difficulties in keyword extraction, and benchmark datasets. The reliability of evaluation techniques and an examination of their flaws remain two of the largest problems. Hence, this study includes the literature that performed a comparative analysis of popular keyword extraction methods. Furthermore, in this paper, we present a comparative evaluation of open-source unsupervised keyword extraction tools, analyzing their performance across a range of data types and under different testing conditions. The experimental analysis shows that, in terms of f-score, KPminer performs most consistently for different text lengths while KeyBERT(mmr) outperforms other tools. Considering the execution time, RAKE and YAKE are the fastest tools. Though graph-based tools tend not to perform well on long text, TopicRank and MultipartiteRank perform very well on long text as they use topics as nodes of the graph, which is another finding of this study. By highlighting the key factors that influence the performance of keyword extraction tools, our analysis contributes to directing the reader in selecting suitable keyword extraction tools for different applications.

show abstract

Section: ) Data Typementioning

confidence: 99%

A Comparative Assessment of Unsupervised Keyword Extraction Tools

Nadim,

Akopian,

Matamoros

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…In the process of identifying named entities, the language in which the text document is written is very important. In the case of languages with an extensive morphological structure, the processing of text documents and the extraction of information is very difficult [12]. Therefore, Graliński et al [13] presented a formalism for the rule-based NER.…”

Section: Introduction and Related Workmentioning

confidence: 99%

Modelling an IT solution to anonymise selected data processed in digital documents

Probierz¹,

Jach²,

Kozák³

et al. 2022

Annals of Computer Science and Information Systems

View full text Add to dashboard Cite

Allowing access to real legal documents is an important element both for the development of science and the judiciary. On the other hand, protecting information about citizens or organizations, that appear in these documents, is crucial and required by law. Therefore, before the documents are distributed, the data anonymisation process should be carried out. Unfortunately, there is no perfect tool that can automatically anonymise documents in such a way, that the main concept of the document is preserved; especially in the case of documents written in inflectional language. The aim of this article is to show how important (and at the same time how difficult) is the task to identify personal or corporate data of a client, as well as other related personal data in documents that are subject to legal protection. We conducted research aimed at assessing the usefulness of IT techniques as well as decision rules and patterns in the anonymisation of legal documents. A set of real legal documents written in Polish was used for the research in which we identified selected types of data that need to be anonymised. Eventually, the obtained results were assessed by field experts. Additionally, in order to verify the effectiveness of the proposed solution, we conducted research on a set of 50,000 false identities with names, company names, addresses and other confidential information. The collection was created using Fake Name Generator 1 . The obtained results from both experiments confirmed that the solutions we proposed is accurate even in the case of real legal documents.

show abstract

Named Entity Recognition in Turkish Bank Documents

Cited by 2 publications

References 18 publications

A Comparative Assessment of Unsupervised Keyword Extraction Tools

A Comparative Assessment of Unsupervised Keyword Extraction Tools

Modelling an IT solution to anonymise selected data processed in digital documents

Contact Info

Product

Resources

About