# An Empirical Evaluation of doc2vec with Practical Insights into Document Embedding Generation

arXiv: https://arxiv.org/abs/1607.05368 · HTML: https://mlsanity.com/paper/1607.05368/

## Key facts

- Cited by 48 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jul 2016.

## Built on by (most cited first, 30 of 48)

- [MDERank: A Masked Document Embedding Rank Approach for Unsupervised Keyphrase Extraction](https://mlsanity.com/paper/2110.06651/) (2021)
- [Identifying Machine-Paraphrased Plagiarism](https://mlsanity.com/paper/2103.11909/) (2021)
- [Diversified Batch Selection for Training Acceleration](https://mlsanity.com/paper/2406.04872/) (2024)
- [Learning Models for Suicide Prediction from Social Media Posts](https://mlsanity.com/paper/2105.03315/) (2021)
- [CarExpert: Leveraging Large Language Models for In-Car Conversational Question Answering](https://mlsanity.com/paper/2310.09536/) (2023)
- [Unsupervised Deep Keyphrase Generation](https://mlsanity.com/paper/2104.08729/) (2021)
- [A News-based Machine Learning Model for Adaptive Asset Pricing](https://mlsanity.com/paper/2106.07103/) (2021)
- [We've had this conversation before: A Novel Approach to Measuring Dialog Similarity](https://mlsanity.com/paper/2110.05780/) (2021)
- [Data Augmentation for Mental Health Classification on Social Media](https://mlsanity.com/paper/2112.10064/) (2021)
- [Lbl2Vec: An Embedding-Based Approach for Unsupervised Document Retrieval on Predefined Topics](https://mlsanity.com/paper/2210.06023/) (2022)
- [SlideSpawn: An Automatic Slides Generation System for Research Publications](https://mlsanity.com/paper/2411.17719/) (2024)
- [Computational thematics: Comparing algorithms for clustering the genres of literary fiction](https://mlsanity.com/paper/2305.11251/) (2023)
- [quantum Case-Based Reasoning (qCBR)](https://mlsanity.com/paper/2104.00409/) (2021)
- [Evaluating Document Representations for Content-based Legal Literature Recommendations](https://mlsanity.com/paper/2104.13841/) (2021)
- [Neural Embeddings of Urban Big Data Reveal Emergent Structures in Cities](https://mlsanity.com/paper/2110.12371/) (2021)
- [EUREKHA: Enhancing User Representation for Key Hackers Identification in Underground Forums](https://mlsanity.com/paper/2411.05479/) (2024)
- [Deep Reversible Consistency Learning for Cross-modal Retrieval](https://mlsanity.com/paper/2501.05686/) (2025)
- [Contextual Text Embeddings for Twi](https://mlsanity.com/paper/2103.15963/) (2021)
- [Stock2Vec: An Embedding to Improve Predictive Models for Companies](https://mlsanity.com/paper/2201.11290/) (2022)
- [Are the Best Multilingual Document Embeddings simply Based on Sentence Embeddings?](https://mlsanity.com/paper/2304.14796/) (2023)
- [Probabilistic Topic Modelling with Transformer Representations](https://mlsanity.com/paper/2403.03737/) (2024)
- [Manufacturing Service Capability Prediction with Graph Neural Networks](https://mlsanity.com/paper/2403.17239/) (2024)
- [Implementing NLPs in industrial process modeling: Addressing Categorical Variables](https://mlsanity.com/paper/2409.19097/) (2024)
- [A Method for Handling Negative Similarities in Explainable Graph Spectral Clustering of Text Documents -- Extended Version](https://mlsanity.com/paper/2504.12360/) (2025)
- [Semantic-Consistent Bidirectional Contrastive Hashing for Noisy Multi-Label Cross-Modal Retrieval](https://mlsanity.com/paper/2511.07780/) (2025)
- [Advances in Electron Microscopy with Deep Learning](https://mlsanity.com/paper/2101.01178/) (2021)
- [Modelling the Impact of Scandals: the case of the 2017 French Presidential Election](https://mlsanity.com/paper/2101.11548/) (2021)
- [Back Translation Survey for Improving Text Augmentation](https://mlsanity.com/paper/2102.09708/) (2021)
- [Bridging the gap between supervised classification and unsupervised topic modelling for social-media assisted crisis management](https://mlsanity.com/paper/2103.11835/) (2021)
- [On Representation Learning for Scientific News Articles Using Heterogeneous Knowledge Graphs](https://mlsanity.com/paper/2104.05866/) (2021)

## Abstract (arXiv)

Recently, Le and Mikolov (2014) proposed doc2vec as an extension to word2vec (Mikolov et al., 2013a) to learn document-level embeddings. Despite promising results in the original paper, others have struggled to reproduce those results. This paper presents a rigorous empirical evaluation of doc2vec over two tasks. We compare doc2vec to two baselines and two state-of-the-art document embedding methodologies. We found that doc2vec performs robustly when using models trained on large external corpora, and can be further improved by using pre-trained word embeddings. We also provide recommendations on hyper-parameter settings for general purpose applications, and release source code to induce document embeddings using our trained doc2vec models.