Skip to content
conftrace_
2020 COLING COLING 2020

ADAPT at SR’20: How Preprocessing and Data Augmentation Help to Improve Surface Realization

Abstract

AbstractIn this paper, we describe the ADAPT submission to the Surface Realization Shared Task 2020. We present a neural-based system trained on the English Web Treebank and an augmented dataset, automatically created from existing text corpora.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Natural Language Processing

Authors

Henry Elder

Topics

Machine Learning > Application Areas > Data Augmentation Deep Learning > Architectures > Neural Networks Natural Language Processing > Generation > Text Generation

Keywords

data augmentation text generation surface realization neural network
Download PDF

More from COLING 2020

All COLING 2020 papers →
Annotating Coherence Relations for Studying Topic Transitions in Social Talk
The Third Multilingual Surface Realisation Shared Task (SR’20): Overview and Evaluation Results
BME-TUW at SR’20: Lexical grammar induction for surface realization
IMSurReal Too: IMS in the Surface Realization Shared Task 2020
Lexical Induction of Morphological and Orthographic Forms for Low-Resourced Languages
NILC at SR’20: Exploring Pre-Trained Models in Surface Realisation