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}
}
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
Highly Cited
This paper has 33 citations. REVIEW CITATIONS

From This Paper

Figures, tables, and topics from this paper.

Citations

Publications citing this paper.
Showing 1-10 of 24 extracted citations

Comparison Study on Critical Components in Composition Model for Phrase Representation

ACM Trans. Asian & Low-Resource Lang. Inf. Process. • 2017
View 2 Excerpts
Highly Influenced

A Neural Approach to Source Dependence Based Context Model for Statistical Machine Translation

IEEE/ACM Transactions on Audio, Speech, and Language Processing • 2018

References

Publications referenced by this paper.
Showing 1-10 of 28 references

Composition in Distributional Models of Semantics

Cognitive Science • 2010
View 10 Excerpts
Highly Influenced

Feature Forest Models for Probabilistic HPSG Parsing

Computational Linguistics • 2008
View 17 Excerpts
Highly Influenced

Adaptive Subgradient Methods for Online Learning and Stochastic Optimization

Journal of Machine Learning Research • 2011
View 2 Excerpts
Highly Influenced

Similar Papers

Loading similar papers…