Papers by Jin-Dong Kim
Mining Biomedical Publications With The LAPPS Grid (L18-1)
Copied to clipboard
| Challenge: | Natural language processing (NLP) text mining can increase productivity and innovation in the sciences by orders of magnitude. |
| Approach: | The Language Applications Grid is an infrastructure for rapid development of natural language processing applications (NLP) it provides an intuitive and easy-to-use platform for users to exploit NLP tools and resources . the Grid integrates the services and resources provided by PubAnnotation to greatly enhance the user's ability to annotate scientific publications . |
| Outcome: | The Language Applications (LAPPS) Grid is an infrastructure for rapid development of natural language processing applications (NLP) it integrates services and resources provided by PubAnnotation to greatly enhance user's ability to annotate scientific publications and share the results. |
COVID-19 Mythbusters in World Languages (2022.lrec-1)
Copied to clipboard
| Challenge: | 115 languages are included in the database, including the original English texts . character bi-grams with normalization is an effective proxy for measuring the similarity of the languages and the affinity ranking of language pairs can be obtained. |
| Approach: | They propose a multi-lingual database containing translated COVID-19 mythbusters texts . they use character bi-grams with normalization to measure similarity of languages . |
| Outcome: | The proposed database has translations into 115 languages and the original English texts, of which the original texts are published by the World Health Organization (WHO). |
Refining and Reusing Annotation Guidelines for LLM Annotation (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) demonstrates remarkable zero-shot annotation tasks . but, they struggle with the specialized conventions of gold-standard benchmarks . |
| Approach: | They propose to reuse and refine annotation guidelines as an alignment mechanism . they propose to use iterative moderation framework to simulate early phases of annotation projects . |
| Outcome: | The proposed framework shows a good potential in effectively refining guidelines, but there is room for improvement. |