English

Primitive Part-of-Speech Tagging using Word Length and Sentential Structure

cmp-lg 2007-05-23 v1 Computation and Language

Abstract

It has been argued that, when learning a first language, babies use a series of small clues to aid recognition and comprehension, and that one of these clues is word length. In this paper we present a statistical part of speech tagger which trains itself solely on the number of letters in each word in a sentence.

Keywords

Cite

@article{arxiv.cmp-lg/9808011,
  title  = {Primitive Part-of-Speech Tagging using Word Length and Sentential Structure},
  author = {Simon Cozens},
  journal= {arXiv preprint arXiv:cmp-lg/9808011},
  year   = {2007}
}

Comments

6 pages

R2 v1 2026-07-22T09:58:59.057Z