20
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Conference Proceedings: not found

      Aspect Sentiment Classification with both Word-level and Clause-level Attention Networks

      proceedings-article
      1 , 2 , 1 , 3 , 1 , 3 , 1
      International Joint Conferences on Artificial Intelligence Organization
      Twenty-Seventh International Joint Conference on Artificial Intelligence {IJCAI-18} (IJCAI-2018)
      Artificial Intelligence
      August 13, 2018 - August 19, 2018

      Read this article at

      ScienceOpenPublisher
      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

          Aspect sentiment classification, a challenging task in sentiment analysis, has been attracting more and more attention in recent years. In this paper, we highlight the need for incorporating the importance degrees of both words and clauses inside a sentence and propose a hierarchical network with both word-level and clause-level attentions to aspect sentiment classification. Specifically, we first adopt sentence-level discourse segmentation to segment a sentence into several clauses. Then, we leverage multiple Bi-directional LSTM layers to encode all clauses and propose a word-level attention layer to capture the importance degrees of words in each clause. Third and finally, we leverage another Bi-directional LSTM layer to encode the outputs from the former layers and propose a clause-level attention layer to capture the importance degrees of all the clauses inside a sentence. Experimental results on the laptop and restaurant datasets from SemEval-2015 demonstrate the effectiveness of our proposed approach to aspect sentiment classification.

          Related collections

          Author and article information

          Conference
          International Joint Conferences on Artificial Intelligence Organization
          July 2018
          July 2018
          : 4439-4445
          Affiliations
          [1 ]School of Computer Science and Technology, Soochow University, China
          [2 ]School of Computer Science and Engineering, Southeast University, China
          [3 ]Alibaba Group, China
          Article
          10.24963/ijcai.2018/617
          4d992ce6-0db6-47da-8dcf-4d1d110e06b2
          © 2018
          Twenty-Seventh International Joint Conference on Artificial Intelligence {IJCAI-18}
          IJCAI-2018
          27
          Stockholm, Sweden
          August 13, 2018 - August 19, 2018
          International Joint Conferences on Artificial Intelligence Organization (IJCAI)
          Artificial Intelligence
          History

          Evolutionary Biology,Medicine
          Evolutionary Biology, Medicine

          Comments

          Comment on this article