Toward Controlled Generation of Text
Generic generation and manipulation of text is challenging and has limited success compared to recent deep generative modeling in visual domain. This paper aims at generating plausible natural language sentences, whose attributes are dynamically controlled by learning disentangled latent representations with designated semantics. We propose a new neural generative model which combines variational auto-encoders and holistic attribute discriminators for effective imposition of semantic structures. With differentiable approximation to discrete text samples, explicit constraints on independent attribute controls, and efficient collaborative learning of generator and discriminators, our model learns highly interpretable representations from even only word annotations, and produces realistic sentences with desired attributes. Quantitative evaluation validates the accuracy of sentence and attribute generation.
Code (3)
Tasks
AttributeSentenceSimilar Papers 제목 키워드 기반
Sequentially Controlled Text Generation
While GPT-2 generates sentences that are remarkably human-like, longer documents can ramble and do not follow human-like writing structure. We study the problem of imposing structure on long-range text. We propose a nove…
Text GenerationSequentially Controlled Text Generation
While GPT2 generates sentences that are remarkably human-like, longer documents can ramble and are structurally different from human-written articles. We study the problem of imposing structure on long-range text. We pro…
ArticlesText GenerationControlled Cue Generation for Play Scripts
In this paper, we use a large-scale play scripts dataset to propose the novel task of theatrical cue generation from dialogues. Using over one million lines of dialogue and cues, we approach the problem of cue generation…
AttributeLanguage ModelingLanguage ModellingText GenerationMulti-Attribute Controlled Text Generation with Contrastive-Generator and External-Discriminator
Though existing researches have achieved impressive results in controlled text generation, they focus mainly on single-attribute control. However, in applications like automatic comments, the topic and sentiment need to …
AttributeComment GenerationText GenerationAn Invariant Learning Characterization of Controlled Text Generation
Controlled generation refers to the problem of creating text that contains stylistic or semantic attributes of interest. Many approaches reduce this problem to training a predictor of the desired attribute. For example, …
AttributeLanguage ModelingLanguage ModellingLarge Language Model+1