Incorporating Pseudo-Parallel Data for Quantifiable Sequence Editing
share
In the task of quantifiable sequence editing (QuaSE), a model needs to edit an input sentence to generate an output that satisfies a given outcome, which is a numerical value measuring a certain property of the output. For example, for review sentences, the outcome could be review ratings; for advertisement, the outcome could be click-through rate. We propose a framework which performs QuaSE by incorporating pseudo-parallel data. Our framework can capture the content similarity and the outcome differences by exploiting pseudo-parallel sentence pairs, which enables a better disentanglement of the latent factors that are relevant to the outcome and thus provides a solid basis to generate output satisfying the desired outcome. The dual reconstruction structure further enhances the capability of generating expected output by exploiting the coupling of latent factors of pseudo-parallel sentences. We prepare a dataset of Yelp review sentences with the ratings as outcome. Experimental results show that our framework can outperform state-of-the-art methods under both sentiment polarity accuracy and target value errors.
READ FULL TEXT