Search Paper
  • Home
  • Login
  • Categories
  • Post URL
  • Academic Resources
  • Contact Us

 

COMPARISON OF TURKISH WORD REPRESENTATIONS TRAINED ON DIFFERENT MORPHOLOGICAL FORMS

google+
Views: 24                 

Author :  Gökhan Güler

Affiliation :  Istanbul Technical University

Country :  Turkey

Category :  Computer Science & Information Technology

Volume, Issue, Month, Year :  10, 01, January, 2020

Abstract :


Increased popularity of different text representations has also brought many improvements in Natural Language Processing (NLP) tasks. Without need of supervised data, embeddings trained on large corpora provide us meaningful relations to be used on different NLP tasks. Even though training these vectors is relatively easy with recent methods, information gained from the data heavily depends on the structure of the corpus language. Since the popularly researched languages have a similar morphological structure, problems occurring for morphologically rich languages are mainly disregarded in studies. For morphologically rich languages, context-free word vectors ignore morphological structure of languages. In this study, we prepared texts in morphologically different forms in a morphologically rich language, Turkish, and compared the results on different intrinsic and extrinsic tasks. To see the effect of morphological structure, we trained word2vec model on texts which lemma and suffixes are treated differently. We also trained subword model fastText and compared the embeddings on word analogy, text classification, sentimental analysis, and language model tasks.

Keyword :  embedding, vector, morphology, Turkish, word2vec, fast

Journal/ Proceedings Name :  Computer Science & Information Technology

URL :  https://aircconline.com/csit/papers/vol10/csit100110.pdf

User Name : alex
Posted 03-04-2021 on 15:30:17 AEDT



Related Research Work

  • Performance Evaluation Of Prince Based Glitch Puf With Several Selection Parts
  • Preventing Forged And Fabricated Academic Credentials Using Cryptography And Qr Codes
  • The Impact Of Ai On The Design Of Reception Robot: A Case Study
  • Topic Tracking And Visualization Method Using Independent Topic Analysis

About Us | Post Cfp | Share URL Main | Share URL category | Post URL
All Rights Reserved @ Call for Papers - Conference & Journals