Data Augmentation with Seq2Seq Models
Paraphrase sparsity is an issue that complicates the training process of question answering systems: syntactically diverse but semantically equivalent sentences can have significant disparities in predicted output probabilities. We propose a method for generating an augmented paraphrase corpus for t...
Main Author: | |
---|---|
Other Authors: | |
Format: | Others |
Published: |
Virginia Tech
2017
|
Subjects: | |
Online Access: | http://hdl.handle.net/10919/78315 |