# Document Embedding with Paragraph Vectors

arXiv: https://arxiv.org/abs/1507.07998 · HTML: https://mlsanity.com/paper/1507.07998/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jul 2015.

## Built on by (most cited first, 13 of 13)

- [HET: Scaling out Huge Embedding Model Training via Cache-enabled Distributed Framework](https://mlsanity.com/paper/2112.07221/) (2021)
- [Cross-domain recommendation via user interest alignment](https://mlsanity.com/paper/2301.11467/) (2023)
- [Lbl2Vec: An Embedding-Based Approach for Unsupervised Document Retrieval on Predefined Topics](https://mlsanity.com/paper/2210.06023/) (2022)
- [Plug-and-Play Document Modules for Pre-trained Models](https://mlsanity.com/paper/2305.17660/) (2023)
- [Document Embedding for Scientific Articles: Efficacy of Word Embeddings vs TFIDF](https://mlsanity.com/paper/2107.05151/) (2021)
- [Skill matching at scale: freelancer-project alignment for efficient multilingual candidate retrieval](https://mlsanity.com/paper/2409.12097/) (2024)
- [An Automated Quality Evaluation Framework of Psychotherapy Conversations with Local Quality Estimates](https://mlsanity.com/paper/2106.07922/) (2021)
- [A Study into patient similarity through representation learning from medical records](https://mlsanity.com/paper/2104.14229/) (2021)
- [Hyperbolic Centroid Calculations for Text Classification](https://mlsanity.com/paper/2211.04462/) (2022)
- [KG-FRUS: a Novel Graph-based Dataset of 127 Years of US Diplomatic Relations](https://mlsanity.com/paper/2311.01606/) (2023)
- [Multi-view user representation learning for user matching without personal information](https://mlsanity.com/paper/2312.14533/) (2023)
- [Fast Exact Retrieval for Nearest-neighbor Lookup (FERN)](https://mlsanity.com/paper/2405.04435/) (2024)
- [Normalisation of SWIFT Message Counterparties with Feature Extraction and Clustering](https://mlsanity.com/paper/2508.21081/) (2025)

## Abstract (arXiv)

Paragraph Vectors has been recently proposed as an unsupervised method for learning distributed representations for pieces of texts. In their work, the authors showed that the method can learn an embedding of movie review texts which can be leveraged for sentiment analysis. That proof of concept, while encouraging, was rather narrow. Here we consider tasks other than sentiment analysis, provide a more thorough comparison of Paragraph Vectors to other document modelling algorithms such as Latent Dirichlet Allocation, and evaluate performance of the method as we vary the dimensionality of the learned representation. We benchmarked the models on two document similarity data sets, one from Wikipedia, one from arXiv. We observe that the Paragraph Vector method performs significantly better than other methods, and propose a simple improvement to enhance embedding quality. Somewhat surprisingly, we also show that much like word embeddings, vector operations on Paragraph Vectors can perform useful semantic results.