# EntropyRank: Unsupervised Keyphrase Extraction via Side-Information Optimization for Language Model-based Text Compression

arXiv: https://arxiv.org/abs/2308.13399 · HTML: https://mlsanity.com/paper/2308.13399/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 29 references that are in the map.
- First posted on arXiv 25 Aug 2023.

## Builds on (most cited first, 9 of 9)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (2020)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [SemEval 2017 Task 10: ScienceIE - Extracting Keyphrases and Relations from Scientific Publications](https://mlsanity.com/paper/1704.02853/) (2017)
- [Simple Unsupervised Keyphrase Extraction using Sentence Embeddings](https://mlsanity.com/paper/1801.04470/) (2018)
- [PatternRank: Leveraging Pretrained Language Models and Part of Speech for Unsupervised Keyphrase Extraction](https://mlsanity.com/paper/2210.05245/) (2022)
- [DZip: improved general-purpose lossless compression based on novel neural network modeling](https://mlsanity.com/paper/1911.03572/) (2019)
- [Theme-weighted Ranking of Keywords from Text Documents using Phrase Embeddings](https://mlsanity.com/paper/1807.05962/) (2018)

## Built on by (most cited first, 2 of 2)

- [A Survey of Resource-efficient LLM and Multimodal Foundation Models](https://mlsanity.com/paper/2401.08092/) (2024)
- [Enhancing Unsupervised Keyword Extraction in Academic Papers through Integrating Highlights with Abstract](https://mlsanity.com/paper/2604.19505/) (2026)

## Abstract (arXiv)

We propose an unsupervised method to extract keywords and keyphrases from texts based on a pre-trained language model (LM) and Shannon's information maximization. Specifically, our method extracts phrases having the highest conditional entropy under the LM. The resulting set of keyphrases turns out to solve a relevant information-theoretic problem: if provided as side information, it leads to the expected minimal binary code length in compressing the text using the LM and an entropy encoder. Alternately, the resulting set is an approximation via a causal LM to the set of phrases that minimize the entropy of the text when conditioned upon it. Empirically, the method provides results comparable to the most commonly used methods in various keyphrase extraction benchmark challenges.