Skip to main content

Word segmentation for the Korean Language

Project description

Package hangul-korean

Hangul is the alphabet for the Korean language. hangul-korean is a package which currently contains a module for segmenting words in written Korean texts.

Segmentation of Korean Words 한국어 낱말 분절

Written Korean texts do employ white space characters. However, more often than not, Korean words occur in a text concatenated immediately to adjacent words without an intervening space character. This low degree of separation of words from each other in writing is due somewhat to an abundance of what linguists call "endoclitics" in the language.

As the language has been subjected to principled and rigorous study for some time, the issue of which strings of sounds, or letters, are words and which are not, has been settled among a small group of selected linguists. This kind of advancement has not been propagated to the general public yet, and nlp engineers working on Korean cannot but make do with whatever inconsistent grammars they happen to have access to. Thus, a major source of difficulty in developing competent Korean text processors has been, and still is, the notion of a word as the smallest syntactic unit.

The WordSegmenter class

The module tokenizer in this package defines the class WordSegmenter. It has, among other things, the following methods:

  • init(modelFile, word2idxFile)
  • infile(fileName)
  • outfile(fileName)
  • inputAsString(aStr)
  • doSegment()
  • segmentedOutput()

After creating a WordSegmenter object, give it a file or a string and then issue wseg.doSegment(). The word-segmented text will be in a file (if specified with outfile()) or in an instance variable accessible via segmentedOutput().

Typical use

from hangul.tokenizer import WordSegmenter

wsg = WordSegmenter()
aPassage = "어휴쟤가 왜저래? 정말우스워죽겠네"  # 문자열을 함수 inputAsString의
wsg.inputAsString (aPassage)                    # 매개변인으로 주거나
# inFile = "tobesegmented"        # 파일 안에 담긴 글을 낱말분할할 때에는 
# wsg.infile(inFile)              # 그 파일 이름을 함수 infile에 넘긴다.
# wsg.outfile("output.txt")
# infile()이 사용되면 낱말 분할 된 글이 적힌 파일이 생겨 난다.
# 이 파일은 함수 outfile()로 지정될 수 있고 디폴트 값은 "segmented_yyddd_hhmm.txt"이다.
# with open("segmented_yyddd_hhmm.txt", "r") as f:
#   lines = f.readlines()
# for aLine in lines:
#   print(aLine)
# inputAsString()이 사용된 경우에는

Forms of a verb are not analyzed into morphs

The lexical category verb is inflected in hundreds (or thousands) of ways in the language and it is the only category that inflects. We do not analyze a form of a verb into its morphs. Such an analysis is best reserved for a separate component of inflectional morphology and is certainly required in order to do syntactic analyses of various kinds.

Forthcoming in the package

The next version of this package might well contain a POS tagger. A raise in the F-measure of the word segmentation system (which currently is somewhere near 0.96) is another thing worth aiming at.

Status of papers that describe this package

A draft is to be submitted to a journal, which describes the way the model for this package is obtained.

Project details

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

hangul-korean-1.0rc1.tar.gz (20.0 kB view hashes)

Uploaded Source

Built Distribution

hangul_korean-1.0rc1-py3-none-any.whl (60.2 MB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page