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

      Language Models as Knowledge Embeddings

      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

          Knowledge embeddings (KE) represent a knowledge graph (KG) by embedding entities and relations into continuous vector spaces. Existing methods are mainly structure-based or description-based. Structure-based methods learn representations that preserve the inherent structure of KGs. They cannot well represent abundant long-tail entities in real-world KGs with limited structural information. Description-based methods leverage textual information and language models. Prior approaches in this direction barely outperform structure-based ones, and suffer from problems like expensive negative sampling and restrictive description demand. In this paper, we propose LMKE, which adopts Language Models to derive Knowledge Embeddings, aiming at both enriching representations of long-tail entities and solving problems of prior description-based methods. We formulate description-based KE learning with a contrastive learning framework to improve efficiency in training and evaluation. Experimental results show that LMKE achieves state-of-the-art performance on KE benchmarks of link prediction and triple classification, especially for long-tail entities.

          Related collections

          Author and article information

          Journal
          25 June 2022
          Article
          2206.12617
          b965547a-2877-4dc8-afb1-31ac7a7c2e14

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

          Custom metadata
          Accepted to IJCAI 2022
          cs.CL cs.AI cs.LG

          Theoretical computer science,Artificial intelligence
          Theoretical computer science, Artificial intelligence

          Comments

          Comment on this article