Ambiguitas machine translation pada cross language chatbot bea cukai

Muhammad Muharrom Al Haromainy, Dimas Ari Setyawan, Onny Kartika Waluya, Agus Zainal Arifin

Research output: Contribution to journalArticlepeer-review


Information retrieval and chatbot systems are increasingly being developed with its language part mostly studied. However, the problem associated with its development is the occurrence of errors in the translation machine resulting in inaccurate answers not in accordance with the natural language, thereby providing users with wrong answers. This study proposes a new translation machine scheme that aims to improve performance while translating ambiguous terms. Translation machines functions by checking the correctness of keywords, and carrying out Part-of-Speech (POS) Tagging on nouns (noun). The synonyms of any detected noun are searched for and obtained added to become alternative new queries. Those with the highest confident value are assumed to be the most appropriate. The results obtained after testing, through the addition of the method proposed in machine translation, can improve the accuracy of the chatbot compared to not using the proposed scheme. The results of the accuracy increased from the original 73% to 77%.

Original languageIndonesian
Pages (from-to)55-62
Number of pages8
JournalRegister: Jurnal Ilmiah Teknologi Sistem Informasi
Issue number1
Publication statusPublished - Jan 2019


  • Ambiguity
  • Chatbot
  • Cross Language
  • Machine translation
  • POS Tagging

Cite this