# BERT Knows Punta Cana is not just beautiful, it's gorgeous: Ranking Scalar Adjectives with Contextualised Representations

arXiv: https://arxiv.org/abs/2010.02686 · HTML: https://mlsanity.com/paper/2010.02686/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Oct 2020.

## Built on by (most cited first, 15 of 15)

- [Unsupervised Contrast-Consistent Ranking with Language Models](https://mlsanity.com/paper/2309.06991/) (2023)
- [Putting Words in BERT's Mouth: Navigating Contextualized Vector Spaces with Pseudowords](https://mlsanity.com/paper/2109.11491/) (2021)
- [Expectations over Unspoken Alternatives Predict Pragmatic Inferences](https://mlsanity.com/paper/2304.04758/) (2023)
- [Representation Of Lexical Stylistic Features In Language Models' Embedding Space](https://mlsanity.com/paper/2305.18657/) (2023)
- [Scalar Adjective Identification and Multilingual Ranking](https://mlsanity.com/paper/2105.01180/) (2021)
- [Life after BERT: What do Other Muppets Understand about Language?](https://mlsanity.com/paper/2205.10696/) (2022)
- [Adjusting Interpretable Dimensions in Embedding Space with Human Judgments](https://mlsanity.com/paper/2404.02619/) (2024)
- [Using Paraphrases to Study Properties of Contextual Embeddings](https://mlsanity.com/paper/2207.05553/) (2022)
- [Probing Large Language Models for Scalar Adjective Lexical Semantics and Scalar Diversity Pragmatics](https://mlsanity.com/paper/2404.03301/) (2024)
- [Rethinking Word Similarity: Semantic Similarity through Classification Confusion](https://mlsanity.com/paper/2502.05704/) (2025)
- [Exploring Data Augmentation Methods on Social Media Corpora](https://mlsanity.com/paper/2303.02198/) (2023)
- [Not wacky vs. definitely wacky: A study of scalar adverbs in pretrained language models](https://mlsanity.com/paper/2305.16426/) (2023)
- [Extracting Conceptual Spaces from LLMs Using Prototype Embeddings](https://mlsanity.com/paper/2509.19269/) (2025)
- [Interpretable dimensions support an effect of agentivity and telicity on split intransitivity](https://mlsanity.com/paper/2511.16824/) (2025)
- [Language Models Learn Constructional Semantics, Not To Mention Syntax: Investigating LM Understanding of Paired-Focus Constructions](https://mlsanity.com/paper/2605.31586/) (2026)

## Abstract (arXiv)

Adjectives like pretty, beautiful and gorgeous describe positive properties of the nouns they modify but with different intensity. These differences are important for natural language understanding and reasoning. We propose a novel BERT-based approach to intensity detection for scalar adjectives. We model intensity by vectors directly derived from contextualised representations and show they can successfully rank scalar adjectives. We evaluate our models both intrinsically, on gold standard datasets, and on an Indirect Question Answering task. Our results demonstrate that BERT encodes rich knowledge about the semantics of scalar adjectives, and is able to provide better quality intensity rankings than static embeddings and previous models with access to dedicated resources.