• Computer Science
• Published in EMNLP 2014
• DOI:10.3115/v1/D14-1163

Jointly Learning Word Representations and Composition Functions Using Predicate-Argument Structures

@inproceedings{Hashimoto2014JointlyLW,
  title={Jointly Learning Word Representations and Composition Functions Using Predicate-Argument Structures},
  author={Kazuma Hashimoto and Pontus Stenetorp and Makoto Miwa and Yoshimasa Tsuruoka},
  booktitle={EMNLP},
  year={2014}
}

• Kazuma Hashimoto, Pontus Stenetorp, +1 author Yoshimasa Tsuruoka

We introduce a novel compositional language model that works on PredicateArgument Structures (PASs). Our model jointly learns word representations and their composition functions using bagof-words and dependency-based contexts. Unlike previous word-sequencebased models, our PAS-based model composes arguments into predicates by using the category information from the PAS. This enables our model to capture longrange dependencies between words and to better handle constructs such as verbobject and… CONTINUE READING

View PDF

Save to Library

Create Alert

Cite