Document separation between native English and nonnative English using long POS strings

Kensei Yukino, Sayaka Aoki, Ryuji Tanigawa, Yoichi Tomiura

Research output: Contribution to journalArticlepeer-review

Abstract

We propose using long and low-frequency part of speech (POS) strings for document separation between native English documents and non-native English documents. The long POS strings were ignored in previous works because their frequencies in training data are too small to estimate their probabilities. Meanwhile, a research of language identification showed that the long and low-frequency byte strings were useful for language identification among similar languages. There are some similarity between language identification and document separation between native English documents and non-native English documents, for example long POS strings are more peculiar to one class than short ones, though there is a difference between POS and byte. Therefore, we can expect higher accuracy by using long and low-frequency POS strings. Some experiments are described in this paper. These experiments show that the proposed method has higher accuracy than previous ones.

Original languageEnglish
Pages (from-to)115-119
Number of pages5
JournalResearch Reports on Information Science and Electrical Engineering of Kyushu University
Volume11
Issue number2
Publication statusPublished - Sep 2006

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering
  • Hardware and Architecture
  • Engineering (miscellaneous)

Fingerprint Dive into the research topics of 'Document separation between native English and nonnative English using long POS strings'. Together they form a unique fingerprint.

Cite this