QuaSE: Accurate Text Style Transfer under Quantifiable Guidance
This work addresses a specific problem in natural language processing for applications like review and advertisement editing, but it is incremental as it builds on existing style transfer and disentanglement methods.
The paper tackles the task of Quantifiable Sequence Editing (QuaSE), which involves editing text to meet a numerical outcome while preserving content, by proposing a framework that disentangles outcome and content factors using pseudo-parallel sentences. The result is demonstrated on a Yelp review dataset with ratings, showing improved performance in generating outputs that satisfy desired outcomes.
We propose the task of Quantifiable Sequence Editing (QuaSE): editing an input sequence to generate an output sequence that satisfies a given numerical outcome value measuring a certain property of the sequence, with the requirement of keeping the main content of the input sequence. For example, an input sequence could be a word sequence, such as review sentence and advertisement text. For a review sentence, the outcome could be the review rating; for an advertisement, the outcome could be the click-through rate. The major challenge in performing QuaSE is how to perceive the outcome-related wordings, and only edit them to change the outcome. In this paper, the proposed framework contains two latent factors, namely, outcome factor and content factor, disentangled from the input sentence to allow convenient editing to change the outcome and keep the content. Our framework explores the pseudo-parallel sentences by modeling their content similarity and outcome differences to enable a better disentanglement of the latent factors, which allows generating an output to better satisfy the desired outcome and keep the content. The dual reconstruction structure further enhances the capability of generating expected output by exploiting the couplings of latent factors of pseudo-parallel sentences. For evaluation, we prepared a dataset of Yelp review sentences with the ratings as outcome. Extensive experimental results are reported and discussed to elaborate the peculiarities of our framework.