Composable Text Controls in Latent Space with ODEs
Document Type
Conference Proceeding
Publication Title
EMNLP 2023 - 2023 Conference on Empirical Methods in Natural Language Processing, Proceedings
Abstract
Real-world text applications often involve composing a wide range of text control operations, such as editing the text w.r.t. an attribute, manipulating keywords and structure, and generating new text of desired properties. Prior work typically learns/finetunes a language model (LM) to perform individual or specific subsets of operations. Recent research has studied combining operations in a plug-and-play manner, often with costly search or optimization in the complex sequence space. This paper proposes a new efficient approach for composable text operations in the compact latent space of text. The low-dimensionality and differentiability of the text latent vector allow us to develop an efficient sampler based on ordinary differential equations (ODEs) given arbitrary plug-in operators (e.g., attribute classifiers). By connecting pretrained LMs (e.g., GPT2) to the latent space through efficient adaption, we then decode the sampled vectors into desired text sequences. The flexible approach permits diverse control operators (sentiment, tense, formality, keywords, etc.) acquired using any relevant data from different domains. Experiments show that composing those operators within our approach manages to generate or edit high-quality text, substantially improving over previous methods in terms of generation quality and efficiency.
First Page
16543
Last Page
16570
Publication Date
1-1-2023
Recommended Citation
G. Liu et al., "Composable Text Controls in Latent Space with ODEs," EMNLP 2023 - 2023 Conference on Empirical Methods in Natural Language Processing, Proceedings, pp. 16543 - 16570, Jan 2023.