# Rethinking Text Attribute Transfer: A Lexical Analysis

arXiv: https://arxiv.org/abs/1909.12335 · HTML: https://mlsanity.com/paper/1909.12335/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Sep 2019.

## Built on by (most cited first, 10 of 10)

- [A Call for Standardization and Validation of Text Style Transfer Evaluation](https://mlsanity.com/paper/2306.00539/) (2023)
- [Non-Parallel Text Style Transfer with Self-Parallel Supervision](https://mlsanity.com/paper/2204.08123/) (2022)
- [Balancing the Style-Content Trade-Off in Sentiment Transfer Using Polarity-Aware Denoising](https://mlsanity.com/paper/2312.14708/) (2023)
- [Evaluating Text Style Transfer Evaluation: Are There Any Reliable Metrics?](https://mlsanity.com/paper/2502.04718/) (2025)
- [From Theories on Styles to their Transfer in Text: Bridging the Gap with a Hierarchical Survey](https://mlsanity.com/paper/2110.15871/) (2021)
- [VAE based Text Style Transfer with Pivot Words Enhancement Learning](https://mlsanity.com/paper/2112.03154/) (2021)
- [Controlling Formality in Low-Resource NMT with Domain Adaptation and Re-Ranking: SLT-CDT-UoS at IWSLT2022](https://mlsanity.com/paper/2205.05990/) (2022)
- [StyleFlow: Disentangle Latent Representations via Normalizing Flow for Unsupervised Text Style Transfer](https://mlsanity.com/paper/2212.09670/) (2022)
- [Stylistic Retrieval-based Dialogue System with Unparallel Training Data](https://mlsanity.com/paper/2109.05477/) (2021)
- [Contextualizing Variation in Text Style Transfer Datasets](https://mlsanity.com/paper/2108.07871/) (2021)

## Abstract (arXiv)

Text attribute transfer is modifying certain linguistic attributes (e.g. sentiment, style, authorship, etc.) of a sentence and transforming them from one type to another. In this paper, we aim to analyze and interpret what is changed during the transfer process. We start from the observation that in many existing models and datasets, certain words within a sentence play important roles in determining the sentence attribute class. These words are referred to as textitthe Pivot Words. Based on these pivot words, we propose a lexical analysis framework, textitthe Pivot Analysis, to quantitatively analyze the effects of these words in text attribute classification and transfer. We apply this framework to existing datasets and models and show that: (1) the pivot words are strong features for the classification of sentence attributes; (2) to change the attribute of a sentence, many datasets only requires to change certain pivot words; (3) consequently, many transfer models only perform the lexical-level modification, while leaving higher-level sentence structures unchanged. Our work provides an in-depth understanding of linguistic attribute transfer and further identifies the future requirements and challenges of this taskfootnoteOur code can be found at https://github.com/FranxYao/pivotanalysis.