QuaSE: Sequence Editing under Quantifiable Guidance
Refereed conference paper presented and published in conference proceedings


摘要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 reviewrating;foranadvertisement,theoutcome 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 sentencetoallowconvenienteditingtochangethe 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.
著者Yi Liao, Lidong Bing, Piji Li, Shuming Shi, Wai Lam, Tong Zhang
會議名稱2018 Conference on Empirical Methods in Natural Language Processing
會議論文集題名Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
頁次3855 - 3864

上次更新時間 2019-02-12 於 08:59