Advancing Seq2seq with Joint Paraphrase Learning

So Yeon Min, Preethi Raghavan, Peter Szolovits


Abstract
We address the problem of model generalization for sequence to sequence (seq2seq) architectures. We propose going beyond data augmentation via paraphrase-optimized multi-task learning and observe that it is useful in correctly handling unseen sentential paraphrases as inputs. Our models greatly outperform SOTA seq2seq models for semantic parsing on diverse domains (Overnight - up to 3.2% and emrQA - 7%) and Nematus, the winning solution for WMT 2017, for Czech to English translation (CzENG 1.6 - 1.5 BLEU).
Anthology ID:
2020.clinicalnlp-1.30
Volume:
Proceedings of the 3rd Clinical Natural Language Processing Workshop
Month:
November
Year:
2020
Address:
Online
Venues:
ClinicalNLP | EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
269–279
Language:
URL:
https://www.aclweb.org/anthology/2020.clinicalnlp-1.30
DOI:
10.18653/v1/2020.clinicalnlp-1.30
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/2020.clinicalnlp-1.30.pdf