Using Word Embeddings in Turkish Part of Speech Tagging

Şevket Can

doi:10.18178/ijmlc.2021.11.5.1063

Abstract

Using Word Embeddings in Turkish Part of Speech Tagging

Highlights

IntroductionPart of speech tagging (POS) is defined as the mapping of words to their corresponding part of speech tags in a text
In natural language processing, part of speech tagging (POS) is defined as the mapping of words to their corresponding part of speech tags in a text
The main difficulty in POS tagging is that a single word may have a different part of speech tag in different sentences based on the contexts

Summary

Introduction

Part of speech tagging (POS) is defined as the mapping of words to their corresponding part of speech tags in a text. Though there exists different categorization in different resources, part of speech tags may be classified in eight main categories in Turkish: noun, verb, adjective, adverb, pronoun, conjunction, question and preposition. The main difficulty in POS tagging is that a single word may have a different part of speech tag in different sentences based on the contexts. This is why POS tag of a word must be determined according to the context. Three sentences are given as examples, where the word “gelecek” should be tagged as adjective, noun and verb with respective to three different meanings Three sentences are given as examples, where the word “gelecek” should be tagged as adjective, noun and verb with respective to three different meanings (Eng. “future”, “” and “will come”)

Methods

Results

Conclusion