Timezone: »

 
Poster
Content preserving text generation with attribute controls
Lajanugen Logeswaran · Honglak Lee · Samy Bengio

Tue Dec 04 07:45 AM -- 09:45 AM (PST) @ Room 517 AB #103
in Tue Poster Session A »

In this work, we address the problem of modifying textual attributes of sentences. Given an input sentence and a set of attribute labels, we attempt to generate sentences that are compatible with the conditioning information. To ensure that the model generates content compatible sentences, we introduce a reconstruction loss which interpolates between auto-encoding and back-translation loss components. We propose an adversarial loss to enforce generated samples to be attribute compatible and realistic. Through quantitative, qualitative and human evaluations we demonstrate that our model is capable of generating fluent sentences that better reflect the conditioning information compared to prior methods. We further demonstrate that the model is capable of simultaneously controlling multiple attributes.

Keywords: Deep Learning · Unsupervised Learning · Adversarial Networks · Generative Models · Natural Language Processing
[ Paper] 

Author Information

Lajanugen Logeswaran (University of Michigan)
Honglak Lee (Google Brain)
Samy Bengio (Google Research, Brain Team)

More from the Same Authors