logo Idiap Research Institute        
 [BibTeX] [Marc21]
Bag-of-Vectors Autoencoders for Unsupervised Conditional Text Generation
Type of publication: Idiap-RR
Citation: Mai_Idiap-RR-21-2021
Number: Idiap-RR-21-2021
Year: 2021
Month: 12
Institution: Idiap
Note: under review at ICLR 2022
Abstract: Text autoencoders are often used for unsupervised conditional text generation by applying mappings in the latent space to change attributes to the desired values. Recently, Mai et al. (2020) proposed Emb2Emb, a method to learn these mappings in the embedding space of an autoencoder. However, their method is restricted to autoencoders with a single-vector embedding, which limits how much information can be retained. We address this issue by extending their method to Bag-of-Vectors Autoencoders (BoV-AEs), which encode the text into a variable-size bag of vectors that grows with the size of the text, as in attention-based models. This allows to encode and reconstruct much longer texts than standard autoencoders. Analogous to conventional autoencoders, we propose regularization techniques that facilitate learning meaningful operations in the latent space. Finally, we adapt Emb2Emb for a training scheme that learns to map an input bag to an output bag, including a novel loss function and neural architecture. Our experimental evaluations on unsupervised sentiment transfer and sentence summarization show that our method performs substantially better than a standard autoencoder.
Keywords: autoencoders, latent space learning, Natural language processing, variable-size
Projects Idiap
Authors Mai, Florian
Henderson, James
Crossref by Mai_AACL_2022
Added by: [ADM]
Total mark: 0