12
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Cross-Lingual Sentiment Analysis Without (Good) Translation

      Preprint
      ,

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          Current approaches to cross-lingual sentiment analysis try to leverage the wealth of labeled English data using bilingual lexicons, bilingual vector space embeddings, or machine translation systems. Here we show that it is possible to use a single linear transformation, with as few as 2000 word pairs, to capture fine-grained sentiment relationships between words in a cross-lingual setting. We apply these cross-lingual sentiment models to a diverse set of tasks to demonstrate their functionality in a non-English context. By effectively leveraging English sentiment knowledge without the need for accurate translation, we can analyze and extract features from other languages with scarce data at a very low cost, thus making sentiment and related analyses for many languages inexpensive.

          Related collections

          Most cited references6

          • Record: found
          • Abstract: not found
          • Conference Proceedings: not found

          Improving Vector Space Word Representations Using Multilingual Correlation

            Bookmark
            • Record: found
            • Abstract: not found
            • Conference Proceedings: not found

            Cross-Lingual Sentiment Classification with Bilingual Document Representation Learning

              Bookmark
              • Record: found
              • Abstract: not found
              • Conference Proceedings: not found

              Learning Bilingual Sentiment Word Embeddings for Cross-language Sentiment Classification

                Bookmark

                Author and article information

                Journal
                2017-07-05
                Article
                1707.01626
                4572d1b3-f5ad-4fb6-8ab6-7f2c54a9b37d

                http://arxiv.org/licenses/nonexclusive-distrib/1.0/

                Custom metadata
                10 pages, 4 figures
                cs.CL

                Theoretical computer science
                Theoretical computer science

                Comments

                Comment on this article