← Back to papers
2019 IJCNLP IJCNLP 2019

Learning to Flip the Sentiment of Reviews from Non-Parallel Corpora

Abstract

AbstractFlipping sentiment while preserving sentence meaning is challenging because parallel sentences with the same content but different sentiment polarities are not always available for model learning. We introduce a method for acquiring imperfectly aligned sentences from non-parallel corpora and propose a model that learns to minimize the sentiment and content losses in a fully end-to-end manner. Our model is simple and offers well-balanced results across two domains: Yelp restaurant and Amazon product reviews.

🌉 Interdisciplinary Bridge — Artificial Intelligence and Deep Learning and Machine Learning and Natural Language Processing
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Security & Privacy, Speech & Audio

Authors

Canasai Kruengkrai

Topics

Artificial Intelligence > Learning Paradigms > Transfer Learning Machine Learning > Learning Types > Unsupervised Learning Machine Learning > Application Areas > Domain Adaptation Deep Learning > Models > Generative Models Natural Language Processing > Generation > Text Generation Natural Language Processing > Applications > Sentiment Analysis

Keywords

unsupervised learning domain adaptation text style transfer content preservation end-to-end model sentiment transfer non-parallel corpus
Download PDF

Related papers

Fine-grained Knowledge Fusion for Sequence Labeling Domain Adaptation 2019
Exploiting Monolingual Data at Scale for Neural Machine Translation 2019
Distributionally Robust Language Modeling 2019
Unsupervised Domain Adaptation of Contextualized Embeddings for Sequence Labeling 2019
ARAML: A Stable Adversarial Training Framework for Text Generation 2019