Paper
6 November 2019 Paraphrase generation and evaluation: a view from the trenches
Author Affiliations +
Proceedings Volume 11176, Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2019; 111761M (2019) https://doi.org/10.1117/12.2535741
Event: Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2019, 2019, Wilga, Poland
Abstract
In this paper we evaluate the current state of the art in natural language paraphrase generation using deep learning methods. The focus is put on the entire modeling pipeline from data gathering up to model evaluation. Specifically, we list the publicly available datasets suitable for this task, assess their quality and discuss procedures connected with data preparation and model training. Finally, we discuss problems related to the currently used evaluation approaches.
© (2019) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Wiktor Franus, Bartłomiej Twardowski, Paweł Zawistowski, and Robert M. Nowak "Paraphrase generation and evaluation: a view from the trenches", Proc. SPIE 11176, Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2019, 111761M (6 November 2019); https://doi.org/10.1117/12.2535741
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Computer programming

Neural networks

Modeling

Computer science

Artificial intelligence

Artificial neural networks

Machine learning

Back to Top