Enhancing Korean Named Entity Recognition With Linguistic Tokenization Strategies

Kim, Gyeongmin; Son, Junyoung; Kim, Jin-Sung; Lee, Hyun‐Hee; Lim, Heuiseok

doi:10.1109/access.2021.3126882

Cited by 13 publications

(7 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Kwon et al (2017) proposed a deep learning based NER system that operates over syllables rather than words, resulting in a speedup by removing the need for morphological analysis. Kim et al (2021) resentations and also found that syllables were the most effective representation for Korean NER.…”

Section: Related Workmentioning

confidence: 91%

UA-KO at SemEval-2022 Task 11: Data Augmentation and Ensembles for Korean Named Entity Recognition

Song¹,

Bethard²

2022

Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)

View full text Add to dashboard Cite

show abstract

Section: Related Workmentioning

confidence: 91%

UA-KO at SemEval-2022 Task 11: Data Augmentation and Ensembles for Korean Named Entity Recognition

Song¹,

Bethard²

2022

Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)

View full text Add to dashboard Cite

show abstract

“…Kim G [19] proposed a novel approach for enhancing Korean Named Entity Recognition (NER) by leveraging linguistic tokenization strategies. The authors address the specific challenges associated with Korean NER and demonstrate the efficacy of their approach through a comprehensive evaluation, showcasing significant performance enhancements compared to baseline methods.…”

Section: Introductionmentioning

confidence: 99%

Semantic Enrichment of Data through Knowledge Graph Generation

Sundaram,

Khalaf,

Regunathan

et al. 2024

Preprint

View full text Add to dashboard Cite

As the Python ecosystem grows, developers encounter a daunting range of open-source packages, often leading to analysis paralysis. A Python Pip package recommender system is proposed that employs a knowledge network and Natural language processing to make customized suggestions, addressing this problem. The study introduces a system to simplify package selection and enhance developer efficiency.The approach relies on a detailed knowledge tree that explains Python package-function relationships. Important features and dependencies are identified by carefully evaluating package information and documentation, resulting in a well-structured network of package interdependencies. The recommendation engine relies on this graph to personalize suggestions based on the user's project needs.The system employs multiple methods to analyze user input and identify project needs using natural language processing. Entity recognition and sentiment analysis are used to understand user intent and goals to make better suggestions. The NLP component dynamically integrates user feedback to improve suggestions and enhance system precision.The system utilizes Python modules like NetworkX for knowledge graph creation, Natural Language Toolkit(NLTK) for NLP processing, and Fast for the web interface. A user-friendly web application allows developers to enter project details and receive Python application recommendations.To evaluate the system's effectiveness, automated testing and user feedback are used. Recommendations are compared against carefully curated package lists for various project categories to assess their accuracy. User happiness is measured by providing extensive input on usability, suggestion quality, and user experience.Finally, the Python Pip package recommender system offers a novel way to enhance developer productivity. Developers are provided with an efficient and accurate package discovery and selection mechanism using a knowledge graph and NLP. The aim is to improve software quality and facilitate Python package adoption with the system.

show abstract

“…In this research, we focus on calculating crypto news sentiment scores and use these calculated scores to enhance the performance of our BTC trading model. Korean language, which is agglutinative in its morphology, is challenging due to the intermediate characteristics positioned between isolating and inflectional language [18]. Basically, an eojeol, which is a spacing unit, consists of more than one morpheme.…”

Section: Introductionmentioning

confidence: 99%

CBITS: Crypto BERT Incorporated Trading System

Kim

Kim²,

Kim

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Most textual analysis-based trading approaches in cryptocurrency (crypto) involve lexical, rule-based methods for extracting news sentiments. Furthermore, general purpose language models (LMs) are not always suitable for the crypto domain due to jargons that are not covered in general purpose texts. This study answers the question of "Is it possible that the LMs can profit by effectively applying the sentiment score of the natural language processing task with chart score in the BTC trading system?" by focusing on the effectiveness of both scores, which significantly affect the profit of the trading system. We introduce CBITS: Cryptocurrency BERT Incorporated Trading System based on pre-trained LMs for Korean crypto sentiment analysis to aid Bitcoin (BTC) trading models. We pre-trained crypto-specific LMs, which are transformer encoder-based architectures. Along with our pre-trained LMs, we also present our custom fine-tuning dataset used to train our LMs on the BTC sentiment classifier and show that using sentiment scores along with BTC chart data boosts the performance of BTC trading models and allows us to create a market neutral trading strategy.

show abstract

Enhancing Korean Named Entity Recognition With Linguistic Tokenization Strategies

Cited by 13 publications

References 31 publications

UA-KO at SemEval-2022 Task 11: Data Augmentation and Ensembles for Korean Named Entity Recognition

UA-KO at SemEval-2022 Task 11: Data Augmentation and Ensembles for Korean Named Entity Recognition

Semantic Enrichment of Data through Knowledge Graph Generation

CBITS: Crypto BERT Incorporated Trading System

Contact Info

Product

Resources

About