# Are "Undocumented Workers" the Same as "Illegal Aliens"? Disentangling Denotation and Connotation in Vector Spaces

arXiv: https://arxiv.org/abs/2010.02976 · HTML: https://mlsanity.com/paper/2010.02976/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Oct 2020.

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

- [The Media Bias Taxonomy: A Systematic Literature Review on the Forms and Automated Detection of Media Bias](https://mlsanity.com/paper/2312.16148/) (2023)
- [Reading Between the Tweets: Deciphering Ideological Stances of Interconnected Mixed-Ideology Communities](https://mlsanity.com/paper/2402.01091/) (2024)
- [How people talk about each other: Modeling Generalized Intergroup Bias and Emotion](https://mlsanity.com/paper/2209.06687/) (2022)
- [No Word Embedding Model Is Perfect: Evaluating the Representation Accuracy for Social Bias in the Media](https://mlsanity.com/paper/2211.03634/) (2022)
- [Controlled Neural Sentence-Level Reframing of News Articles](https://mlsanity.com/paper/2109.04957/) (2021)
- [Bridging Dictionary: AI-Generated Dictionary of Partisan Language Use](https://mlsanity.com/paper/2407.09661/) (2024)
- [Detecting Polarized Topics Using Partisanship-aware Contextualized Topic Embeddings](https://mlsanity.com/paper/2104.07814/) (2021)
- [Counterfactual Probing for the Influence of Affect and Specificity on Intergroup Bias](https://mlsanity.com/paper/2305.16409/) (2023)
- [Structuring the Space of Perspectives](https://mlsanity.com/paper/2608.12113/) (2026)
- [TIDE: Textual Identity Detection for Evaluating and Augmenting Classification and Language Models](https://mlsanity.com/paper/2309.04027/) (2023)

## Abstract (arXiv)

In politics, neologisms are frequently invented for partisan objectives. For example, "undocumented workers" and "illegal aliens" refer to the same group of people (i.e., they have the same denotation), but they carry clearly different connotations. Examples like these have traditionally posed a challenge to reference-based semantic theories and led to increasing acceptance of alternative theories (e.g., Two-Factor Semantics) among philosophers and cognitive scientists. In NLP, however, popular pretrained models encode both denotation and connotation as one entangled representation. In this study, we propose an adversarial neural network that decomposes a pretrained representation as independent denotation and connotation representations. For intrinsic interpretability, we show that words with the same denotation but different connotations (e.g., "immigrants" vs. "aliens", "estate tax" vs. "death tax") move closer to each other in denotation space while moving further apart in connotation space. For extrinsic application, we train an information retrieval system with our disentangled representations and show that the denotation vectors improve the viewpoint diversity of document rankings.