Visible to the public Fair Transfer of Multiple Style Attributes in Text

TitleFair Transfer of Multiple Style Attributes in Text
Publication TypeConference Paper
Year of Publication2019
AuthorsDabas, K., Madaan, N., Arya, V., Mehta, S., Chakraborty, T., Singh, G.
Conference Name2019 Grace Hopper Celebration India (GHCI)
Date PublishedNov. 2019
ISBN Number 978-1-7281-4264-7
Keywordscommunication style, Decoding, Deep Learning, fair transfer, Focusing, Indexes, machine learning, Metrics, multi-style transfer, natural language processing, neural net architecture, neural network architecture, Neural networks, neural style transfer, one-style transfer, pubcrawl, resilience, Resiliency, Scalability, single-style transfers, style attributes, target text, text analysis, text generation, text style transfer, Training, Writing, written text, Yelp dataset

To preserve anonymity and obfuscate their identity on online platforms users may morph their text and portray themselves as a different gender or demographic. Similarly, a chatbot may need to customize its communication style to improve engagement with its audience. This manner of changing the style of written text has gained significant attention in recent years. Yet these past research works largely cater to the transfer of single style attributes. The disadvantage of focusing on a single style alone is that this often results in target text where other existing style attributes behave unpredictably or are unfairly dominated by the new style. To counteract this behavior, it would be nice to have a style transfer mechanism that can transfer or control multiple styles simultaneously and fairly. Through such an approach, one could obtain obfuscated or written text incorporated with a desired degree of multiple soft styles such as female-quality, politeness, or formalness. To the best of our knowledge this work is the first that shows and attempt to solve the issues related to multiple style transfer. We also demonstrate that the transfer of multiple styles cannot be achieved by sequentially performing multiple single-style transfers. This is because each single style-transfer step often reverses or dominates over the style incorporated by a previous transfer step. We then propose a neural network architecture for fairly transferring multiple style attributes in a given text. We test our architecture on the Yelp dataset to demonstrate our superior performance as compared to existing one-style transfer steps performed in a sequence.

Citation Keydabas_fair_2019