{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/an-empirical-evaluation-of-doc2vec-with","title":"An Empirical Evaluation of doc2vec with Practical Insights into Document Embedding Generation","arxiv_id":"1607.05368","date":"2016-07-19","proceeding":"WS 2016 8","authors":["Jey Han Lau","Timothy Baldwin"],"abstract":"Recently, Le and Mikolov (2014) proposed doc2vec as an extension to word2vec\n(Mikolov et al., 2013a) to learn document-level embeddings. Despite promising\nresults in the original paper, others have struggled to reproduce those\nresults. This paper presents a rigorous empirical evaluation of doc2vec over\ntwo tasks. We compare doc2vec to two baselines and two state-of-the-art\ndocument embedding methodologies. We found that doc2vec performs robustly when\nusing models trained on large external corpora, and can be further improved by\nusing pre-trained word embeddings. We also provide recommendations on\nhyper-parameter settings for general purpose applications, and release source\ncode to induce document embeddings using our trained doc2vec models.","url_abs":"http://arxiv.org/abs/1607.05368v1","url_pdf":"http://arxiv.org/pdf/1607.05368v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"an-empirical-evaluation-of-doc2vec-with","repo_url":"https://github.com/jhlau/doc2vec","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"an-empirical-evaluation-of-doc2vec-with","repo_url":"https://github.com/sreejukomath/NLPProjects","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"an-empirical-evaluation-of-doc2vec-with","repo_url":"https://github.com/tsandefer/capstone_2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"an-empirical-evaluation-of-doc2vec-with","repo_url":"https://github.com/tsandefer/dsi_capstone_2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"document-embedding","task_name":"Document Embedding"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1607.05368","atlas_url":"https://app.syntology.ai/?focus=1607.05368","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}