%0 Generic %1 lau2016empirical %A Lau, Jey Han %A Baldwin, Timothy %D 2016 %K doc2vec fakenews %T An Empirical Evaluation of doc2vec with Practical Insights into Document Embedding Generation %U http://arxiv.org/abs/1607.05368 %X 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.

@misc{lau2016empirical, 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.}, added-at = {2017-02-28T12:04:06.000+0100}, author = {Lau, Jey Han and Baldwin, Timothy}, biburl = {https://www.bibsonomy.org/bibtex/2af3c2a80cf9139a541308611ea5b7162/albinzehe}, description = {[1607.05368] An Empirical Evaluation of doc2vec with Practical Insights into Document Embedding Generation Pretrained doc2vec models available from https://github.com/jhlau/doc2vec}, interhash = {ffa9ea0ab141686bb174a4c165cda0f9}, intrahash = {af3c2a80cf9139a541308611ea5b7162}, keywords = {doc2vec fakenews}, note = {cite arxiv:1607.05368Comment: 1st Workshop on Representation Learning for NLP}, timestamp = {2017-02-28T12:04:06.000+0100}, title = {An Empirical Evaluation of doc2vec with Practical Insights into Document Embedding Generation}, url = {http://arxiv.org/abs/1607.05368}, year = 2016 }