Tweet2Vec: Character-Based Distributed Representations for Social Media
Abstract
Text from social media provides a set of challenges that can cause traditional NLP approaches to fail. Informal language, spelling errors, abbreviations, and special characters are all commonplace in these posts, leading to a prohibitively large vocabulary size for word-level approaches. We propose a character composition model, tweet2vec, which finds vector-space representations of whole tweets by learning complex, non-local dependencies in character sequences. The proposed model outperforms a word-level baseline at predicting user-annotated hashtags associated with the posts, doing significantly better when the input contains many out-of-vocabulary words or unusual character sequences. Our tweet2vec encoder is publicly available.
Cite
@article{arxiv.1605.03481,
title = {Tweet2Vec: Character-Based Distributed Representations for Social Media},
author = {Bhuwan Dhingra and Zhong Zhou and Dylan Fitzpatrick and Michael Muehl and William W. Cohen},
journal= {arXiv preprint arXiv:1605.03481},
year = {2016}
}
Comments
6 pages, 2 figures, 4 tables, accepted as conference paper at ACL 2016