Semantic Role Labeling with Neural Network Factors
Autor: | Nicholas FitzGerald, Oscar Täckström, Dipanjan Das, Kuzman Ganchev |
---|---|
Rok vydání: | 2015 |
Předmět: |
Artificial neural network
Computer science business.industry Predicate (mathematical logic) Machine learning computer.software_genre Task (project management) PropBank Semantic role labeling Graphical model Artificial intelligence FrameNet Structured prediction business computer Natural language processing |
Zdroj: | EMNLP |
Popis: | We present a new method for semantic role labeling in which arguments and semantic roles are jointly embedded in a shared vector space for a given predicate. These embeddings belong to a neural network, whose output represents the potential functions of a graphical model designed for the SRL task. We consider both local and structured learning methods and obtain strong results on standard PropBank and FrameNet corpora with a straightforward product-of-experts model. We further show how the model can learn jointly from PropBank and FrameNet annotations to obtain additional improvements on the smaller FrameNet dataset. |
Databáze: | OpenAIRE |
Externí odkaz: |