In this paper, we present a system which can extract syntactic feature structures from a Korean T... more In this paper, we present a system which can extract syntactic feature structures from a Korean Treebank (Sejong Tree- bank) to develop a Feature-based Lexi- calized Tree Adjoining Grammars.
2011 International Conference on Information Science and Applications, 2011
... Jeong-Won Cha Department of Computer Engineering Changwon National University Changwon, Repub... more ... Jeong-Won Cha Department of Computer Engineering Changwon National University Changwon, Republic of Korea [email protected] ... 화제/NNG+가/JKC hwajae +gai ('a issue') NNG - - JKC VV NP_CMP 되/VV+었었/EP+다/EF+./SF doi +ettett + da + . ...
Proceedings of the 5th International Workshop on Semantic Evaluation, ACL 2010, pages 178181, Up... more Proceedings of the 5th International Workshop on Semantic Evaluation, ACL 2010, pages 178181, Uppsala, Sweden, 15-16 July 2010. cO2010 Association for Computational Linguistics ... UNPMC: Naıve Approach to Extract Keyphrases from Scientific Articles
Interlinking data coming from different sources has been a long standing goal [4] aiming to incre... more Interlinking data coming from different sources has been a long standing goal [4] aiming to increase reusability, discoverability, and as a result the usefulness of information. Nowadays, Linked Open Data (LOD) tackles this issue in the context of semantic web. However, currently most of the web data is stored in relational databases and published as unstructured text. This triggers the need of (i) combining the current semantic technologies with relational databases; (ii) processing text integrating several NLP tools, and being able to query the outcome using the standard semantic web query language: SPARQL; and (iii) linking the outcome with the LOD cloud. The work presented here shows a solution for the needs listed above in the context of Korean language, but our approach can be adapted to other languages as well.
In this document, we propose a new unique and universal identification schema for Language Resour... more In this document, we propose a new unique and universal identification schema for Language Resources to provide Language Resources with unique names using a standardized nomenclature. This will also ensure Language Resources to be identified, and consequently to be recognized with proper references in activities within Human Language Technologies as well as in documents and scientific papers.
We live in the age of information deluge. While people can access information through these web s... more We live in the age of information deluge. While people can access information through these web services, at the very same time they used to face unknown words, which they do not know their meaning. A part of these kind words could be newly coined words, such as ...
This project is funded under the eContentplus programme 1 , a multiannual Community programme to ... more This project is funded under the eContentplus programme 1 , a multiannual Community programme to make digital content in Europe more accessible, usable and exploitable.
In this paper, we present a system which can extract syntactic feature structures from a Korean T... more In this paper, we present a system which can extract syntactic feature structures from a Korean Treebank (Sejong Tree- bank) to develop a Feature-based Lexi- calized Tree Adjoining Grammars.
2011 International Conference on Information Science and Applications, 2011
... Jeong-Won Cha Department of Computer Engineering Changwon National University Changwon, Repub... more ... Jeong-Won Cha Department of Computer Engineering Changwon National University Changwon, Republic of Korea [email protected] ... 화제/NNG+가/JKC hwajae +gai ('a issue') NNG - - JKC VV NP_CMP 되/VV+었었/EP+다/EF+./SF doi +ettett + da + . ...
Proceedings of the 5th International Workshop on Semantic Evaluation, ACL 2010, pages 178181, Up... more Proceedings of the 5th International Workshop on Semantic Evaluation, ACL 2010, pages 178181, Uppsala, Sweden, 15-16 July 2010. cO2010 Association for Computational Linguistics ... UNPMC: Naıve Approach to Extract Keyphrases from Scientific Articles
Interlinking data coming from different sources has been a long standing goal [4] aiming to incre... more Interlinking data coming from different sources has been a long standing goal [4] aiming to increase reusability, discoverability, and as a result the usefulness of information. Nowadays, Linked Open Data (LOD) tackles this issue in the context of semantic web. However, currently most of the web data is stored in relational databases and published as unstructured text. This triggers the need of (i) combining the current semantic technologies with relational databases; (ii) processing text integrating several NLP tools, and being able to query the outcome using the standard semantic web query language: SPARQL; and (iii) linking the outcome with the LOD cloud. The work presented here shows a solution for the needs listed above in the context of Korean language, but our approach can be adapted to other languages as well.
In this document, we propose a new unique and universal identification schema for Language Resour... more In this document, we propose a new unique and universal identification schema for Language Resources to provide Language Resources with unique names using a standardized nomenclature. This will also ensure Language Resources to be identified, and consequently to be recognized with proper references in activities within Human Language Technologies as well as in documents and scientific papers.
We live in the age of information deluge. While people can access information through these web s... more We live in the age of information deluge. While people can access information through these web services, at the very same time they used to face unknown words, which they do not know their meaning. A part of these kind words could be newly coined words, such as ...
This project is funded under the eContentplus programme 1 , a multiannual Community programme to ... more This project is funded under the eContentplus programme 1 , a multiannual Community programme to make digital content in Europe more accessible, usable and exploitable.
Uploads
Papers by jungyeul park