Year: 2016
Type: conference-paper
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 vectorspace 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 outof-vocabulary words or unusual character sequences.Our tweet2vec encoder is publicly available 1 .
DOI: 10.18653/v1/p16-2044
Institutions: Qualcomm (United Kingdom), Carnegie Mellon University
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W2371282818
