Method evidence record

FastText

FastText is a word embedding and text classification framework developed by Facebook AI Research (Joulin, Bojanowski, Grave, and Mikolov, 2016–2017) that represents each word as the sum of its character n-gram vectors, allowing it to construct meaningful representations for unseen and morphologically rich words and to perform near state-of-the-art text classification orders of magnitude faster than deep neural network alternatives.

Sources recorded, not reviewed

Source record

Citations copied verbatim from the method’s source record. No claim-level verification is inferred from them.

FastText: Subword-Level Word Embeddings and Efficient Text Classification

Taxonomic method record · ml-model / deep-learning

Joulin, A., Grave, E., Bojanowski, P. & Mikolov, T. (2017). Bag of Tricks for Efficient Text Classification. In Proceedings of EACL 2017, Short Papers, pp. 427–431. ACL. · DOI 10.18653/v1/e17-2068
Bojanowski, P., Grave, E., Joulin, A. & Mikolov, T. (2017). Enriching Word Vectors with Subword Information. Transactions of the Association for Computational Linguistics, 5, 135–146. · DOI 10.1162/tacl_a_00051
Goldberg, Y. (2017). Neural Network Methods for Natural Language Processing. Morgan & Claypool Publishers. · ISBN 978-1-62705-298-6

Open full method

Curated claims

Claims persisted in the evidence ledger, each with its own assessment.

No curated claims yet

This view does not invent a claim assessment when the ledger has none.

Related methods

Generated from the method graph and shown as machine-suggested relations — no evidence claim is inferred.

Same method familyNaive Bayesmachine-suggested · Relational suggestion, not evidence.See alsoWord2Vecmachine-suggested · Relational suggestion, not evidence.