Applications of Tf-idf concept to improve monolingual and cross-language information retrieval based on word embeddings

Syandra Sari, Mirna Adriani

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This work applied word embeddings for English monolingual information retrieval and Dutch-English cross-language information retrieval. Besides word embeddings, this work also applied tf-idf concept to increase result of relevant documents. We present experiments using four techniques adapted from tf-idf concept. The result showed additional techniques could increase MAP score up to 26.6% in monolingual information retrieval and up to 26.2% in cross-language information retrieval compare with monolingual information retrieval and cross-language information retrieval using average vectors technique only.

Original languageEnglish
Title of host publicationProceedings of the International Conference on Advanced Information Science and System, AISS 2019
PublisherAssociation for Computing Machinery
ISBN (Electronic)9781450372916
DOIs
Publication statusPublished - 15 Nov 2019
Event2019 International Conference on Advanced Information Science and System, AISS 2019 - Singapore, Singapore
Duration: 15 Nov 201917 Nov 2019

Publication series

NameACM International Conference Proceeding Series

Conference

Conference2019 International Conference on Advanced Information Science and System, AISS 2019
CountrySingapore
CitySingapore
Period15/11/1917/11/19

Keywords

  • Cross-Language Information Retrieval
  • Cross-Lingual Word Embeddings
  • Monolingual Information Retrieval
  • Tf-Idf
  • Word Embeddings

Fingerprint Dive into the research topics of 'Applications of Tf-idf concept to improve monolingual and cross-language information retrieval based on word embeddings'. Together they form a unique fingerprint.

Cite this