# Comparative Analysis of Document-Level Embedding Methods for Similarity Scoring on Shakespeare Sonnets and Taylor Swift Lyrics

arXiv: https://arxiv.org/abs/2412.17552 · HTML: https://mlsanity.com/paper/2412.17552/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 22 references that are in the map.
- First posted on arXiv 23 Dec 2024.

## Builds on (most cited first, 6 of 6)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [Distributed Representations of Sentences and Documents](https://mlsanity.com/paper/1405.4053/) (2014)
- [Text Similarity in Vector Space Models: A Comparative Study](https://mlsanity.com/paper/1810.00664/) (2018)

## Abstract (arXiv)

This study evaluates the performance of TF-IDF weighting, averaged Word2Vec embeddings, and BERT embeddings for document similarity scoring across two contrasting textual domains. By analysing cosine similarity scores, the methods' strengths and limitations are highlighted. The findings underscore TF-IDF's reliance on lexical overlap and Word2Vec's superior semantic generalisation, particularly in cross-domain comparisons. BERT demonstrates lower performance in challenging domains, likely due to insufficient domainspecific fine-tuning.