Blog
About

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

      DSGAN: Generative Adversarial Training for Distant Supervision Relation Extraction

      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

          Distant supervision can effectively label data for relation extraction, but suffers from the noise labeling problem. Recent works mainly perform soft bag-level noise reduction strategies to find the relatively better samples in a sentence bag, which is suboptimal compared with making a hard decision of false positive samples in sentence level. In this paper, we introduce an adversarial learning framework, which we named DSGAN, to learn a sentence-level true-positive generator. Inspired by Generative Adversarial Networks, we regard the positive samples generated by the generator as the negative samples to train the discriminator. The optimal generator is obtained until the discrimination ability of the discriminator has the greatest decline. We adopt the generator to filter distant supervision training dataset and redistribute the false positive instances into the negative set, in which way to provide a cleaned dataset for relation classification. The experimental results show that the proposed strategy significantly improves the performance of distant supervision relation extraction comparing to state-of-the-art systems.

          Related collections

          Most cited references 8

          • Record: found
          • Abstract: not found
          • Article: not found

          Distant supervision for relation extraction without labeled data

            Bookmark
            • Record: found
            • Abstract: not found
            • Article: not found

            Incorporating non-local information into information extraction systems by Gibbs sampling

              Bookmark
              • Record: found
              • Abstract: not found
              • Book Chapter: not found

              Modeling Relations and Their Mentions without Labeled Text

                Bookmark

                Author and article information

                Journal
                24 May 2018
                Article
                1805.09929

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

                Custom metadata
                cs.CL

                Theoretical computer science

                Comments

                Comment on this article