Published January 1, 2018 | Version v1
Conference paper Open

A Cross-Lingual Approach for Building Multilingual Sentiment Lexicons

  • 1. Hacettepe Univ, TR-06800 Ankara, Turkey
  • 2. Univ Dusseldorf, DFG SFB 991, Dusseldorf, Germany

Description

We propose a cross-lingual distributional model to build sentiment lexicons in many languages from resources available in English. We evaluate this method for two languages, German and Turkish, and on several datasets. We show that the sentiment lexicons built using our method remarkably improve the performance of a state-of-the-art lexicon-based BiLSTM sentiment classifier.

Files

bib-8d880747-9a8a-46da-b6db-b21f2986188d.txt

Files (178 Bytes)

Name Size Download all
md5:85358d950d1f057350e24e598c9856c6
178 Bytes Preview Download