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

ACL ID D14-1163
Title Jointly Learning Word Representations and Composition Functions Using Predicate-Argument Structures
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2014
Authors

We introduce a novel compositional lan- guage model that works on Predicate- Argument Structures (PASs). Our model jointly learns word representations and their composition functions using bag- of-words and dependency-based con- texts. Unlike previous word-sequence- based models, our PAS-based model com- poses arguments into predicates by using the category information from the PAS. This enables our model to capture long- range dependencies between words and to better handle constructs such as verb- object and subject-verb-object relations. We verify this experimentally using two phrase similarity datasets and achieve re- sults comparable to or higher than the pre- vious best results. Our system achieves these results without the need for pre- trained word vectors and using a much smaller ...