Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Unlocking Korean Verbs: A User-Friendly Exploration into the Verb Lexicon

Seohyun Song, Eunkyul Leah Jo, Yige Chen, Jeen-Pyo Hong, Kyuwon Kim, Jin Wee, Miyoung Kang, KyungTae Lim, Jungyeul Park, Chulwoo Park

TL;DR

The paper addresses making the Sejong dictionary's Korean verb subcategorization frames more usable for NLP by presenting a user-friendly web interface and a Python library (pySejongFrame). It details how the web interface maps subcategorization frames to sentence examples, while the library offers direct and lazy loading, NLTK integration, and robust corpus querying for frame semantics. It also positions Sejong relative to PropBank, NIKL SRL, and FrameNet, and outlines future plans to integrate additional resources toward a Korean VerbNet. The work aims to broaden access to Korean linguistic resources and support diverse language-processing applications, while noting licensing and static-data limitations.

Abstract

The Sejong dictionary dataset offers a valuable resource, providing extensive coverage of morphology, syntax, and semantic representation. This dataset can be utilized to explore linguistic information in greater depth. The labeled linguistic structures within this dataset form the basis for uncovering relationships between words and phrases and their associations with target verbs. This paper introduces a user-friendly web interface designed for the collection and consolidation of verb-related information, with a particular focus on subcategorization frames. Additionally, it outlines our efforts in mapping this information by aligning subcategorization frames with corresponding illustrative sentence examples. Furthermore, we provide a Python library that would simplify syntactic parsing and semantic role labeling. These tools are intended to assist individuals interested in harnessing the Sejong dictionary dataset to develop applications for Korean language processing.

Unlocking Korean Verbs: A User-Friendly Exploration into the Verb Lexicon

TL;DR

The paper addresses making the Sejong dictionary's Korean verb subcategorization frames more usable for NLP by presenting a user-friendly web interface and a Python library (pySejongFrame). It details how the web interface maps subcategorization frames to sentence examples, while the library offers direct and lazy loading, NLTK integration, and robust corpus querying for frame semantics. It also positions Sejong relative to PropBank, NIKL SRL, and FrameNet, and outlines future plans to integrate additional resources toward a Korean VerbNet. The work aims to broaden access to Korean linguistic resources and support diverse language-processing applications, while noting licensing and static-data limitations.

Abstract

The Sejong dictionary dataset offers a valuable resource, providing extensive coverage of morphology, syntax, and semantic representation. This dataset can be utilized to explore linguistic information in greater depth. The labeled linguistic structures within this dataset form the basis for uncovering relationships between words and phrases and their associations with target verbs. This paper introduces a user-friendly web interface designed for the collection and consolidation of verb-related information, with a particular focus on subcategorization frames. Additionally, it outlines our efforts in mapping this information by aligning subcategorization frames with corresponding illustrative sentence examples. Furthermore, we provide a Python library that would simplify syntactic parsing and semantic role labeling. These tools are intended to assist individuals interested in harnessing the Sejong dictionary dataset to develop applications for Korean language processing.
Paper Structure (17 sections, 5 figures, 1 table)

This paper contains 17 sections, 5 figures, 1 table.

Table of Contents

  1. Introduction
  2. Previous work
  3. Subcategorization frames
  4. Previous usages of the Sejong dictionary
  5. Developing a Web Interface
  6. Python Library
  7. Library initialization
  8. Loading methods
  9. Direct loading using SejongFrameCorpusReader
  10. Lazy loading with LazyClassLoader
  11. Integration with nltk
  12. Corpus querying and usage
  13. Exploring Frame Semantics
  14. Error handling and best practices
  15. Performance considerations
  16. ...and 2 more sections

Figures (5)

  • Figure 1: Example from the Sejong dictionary: 확립하다hwaglibhada ('establish')
  • Figure 2: Example of subcategorziation frame to sentence projection
  • Figure 3: Interface screenshot of a typical word details page including morphological, semantic, and syntactic frame information along with their associated semantic roles and sentence examples.
  • Figure 4: Subcategorization frames of the verb, along with its semantic role information for arguments, including chunked structures based on frame information to identify argument boundaries
  • Figure 5: First page of the web interface, which allows users to search for Korean verbs