An Empirical Evaluation of doc2vec with Practical Insights into Document Embedding Generation
Year: 2016
Type: conference-paper
Abstract: 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.
DOI: 10.18653/v1/w16-1609
Authors: Jey Han Lau, Timothy Baldwin
Institutions: King's College London, The University of Melbourne
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2480068437