StylePTB: A Compositional Benchmark for Fine-grained Controllable Text Style Transfer
By Yiwei Lyu, Percy Liang, Hai Pham, Eduard H. Hovy, Barnab'as P'oczos, Ruslan Salakhutdinov, Louis-philippe Morency. 2021
48 citations recorded by the source corpus.
Text style transfer aims to controllably generate text with targeted stylistic changes while maintaining core meaning from the source sentence constant. Many of the existing style transfer benchmarks primarily focus on individual high-level semantic changes (e.g. positive to negative), which enable controllability at a high level but do not offer fine-grained control involving sentence structure, emphasis, and content of the sentence. In this paper, we introduce a large-scale benchmark, StylePTB, with (1) paired sentences undergoing 21 fine-grained stylistic changes spanning atomic lexical, syntactic, semantic, and thematic transfers of text, as well as (2) compositions of multiple transfers which allow modeling of fine-grained stylistic changes as building blocks for more complex, high-level transfers. By benchmarking existing methods on StylePTB, we find that they struggle to model fine-grained changes and have an even more difficult time composing multiple styles. As a result, StylePTB brings novel challenges that we hope will encourage future research in controllable text style transfer, compositional models, and learning disentangled representations. Solving these challenges would present important steps towards controllable text generation.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Matt Gardner
- Matthew E. Peters
- Hao Peng
- Tongshuang Sherry Wu
- Alexis Ross
- Mohit Bansal
- Noah A. Smith
- Luke S. Zettlemoyer
In Computer Vision and Pattern Recognition
- Matthew E. Peters
- Matt Gardner
- Hao Peng
- Alexis Ross
- Tongshuang Sherry Wu
- Yonatan Belinkov
- Hannaneh Hajishirzi
- Jonathan Berant
In Natural Language Processing
- Matt Gardner
- Matthew E. Peters
- Tongshuang Sherry Wu
- Hao Peng
- Alexis Ross
- Mohit Bansal
- Luke S. Zettlemoyer
- Jonathan Berant
Citations in the corpus
- Tailor: Generating and Perturbing Text with Semantic Controls (2021, methodology): “We evaluate T ailor without any finetuning on the S tyle PTB benchmark (Lyu et al., 2021), which builds on the Penn Treebank and assesses both single , fine-grained transfers ( e.g., To Future Tense ) and compositional ones that concurrently edit multiple dimensions ( e.g., To Future Tense + Active To”
- Sequence-to-Sequence Learning with Latent Neural Grammars (2021, unknown): “We next apply our approach on style transfer on English utilizing the StylePTB dataset from Lyu et al. [78].”