Skip to content
conftrace_
2018 ACL ACL 2018

AX Semantics’ Submission to the Surface Realization Shared Task 2018

Abstract

AbstractIn this paper we describe our system and experimental results on the development set of the Surface Realisation Shared Task. Our system is an entry for the Shallow-Task, with two different models based on deep-learning implementations for building the sentence combined with a rule-based morphology component.

Authors

Andreas Madsack, Johanna Heininger, Nyamsuren Davaasambuu, Vitaliia Voronik, Michael Käufl, Robert Weißgraeber

Topics

Machine Learning > Core Methods > Classification

Keywords

deep learning rule-based system surface realization sentence generation sentence construction rule-based morphology shallow task
Download PDF

More from ACL 2018

All ACL 2018 papers →
Surface Realization Shared Task 2018 (SR18): The Tilburg University Approach
The OSU Realizer for SRST ‘18: Neural Sequence-to-Sequence Inflection and Incremental Locality-Based Linearization
Generating High-Quality Surface Realizations Using Data Augmentation and Factored Sequence Models
NILC-SWORNEMO at the Surface Realization Shared Task: Exploring Syntax-Based Word Ordering using Neural Models
The DipInfo-UniTo system for SRST 2018
Probabilistic FastText for Multi-Sense Word Embeddings