Abstract | ||
---|---|---|
Microblog normalisation methods often utilise complex models and struggle to differentiate between correctly-spelled unknown words and lexical variants of known words. In this paper, we propose a method for constructing a dictionary of lexical variants of known words that facilitates lexical normalisation via simple string substitution (e.g. tomorrow for tmrw). We use context information to generate possible variant and normalisation pairs and then rank these by string similarity. Highly-ranked pairs are selected to populate the dictionary. We show that a dictionary-based approach achieves state-of-the-art performance for both F-score and word error rate on a standard dataset. Compared with other methods, this approach offers a fast, lightweight and easy-to-use solution, and is thus suitable for high-volume microblog pre-processing. |
Year | Venue | Keywords |
---|---|---|
2012 | EMNLP-CoNLL | microblog normalisation method,context information,simple string substitution,lexical variant,normalisation pair,normalisation dictionary,dictionary-based approach,string similarity,lexical normalisation,known word,highly-ranked pair |
Field | DocType | Volume |
Social media,Computer science,Word error rate,Microblogging,Speech recognition,Natural language processing,Artificial intelligence,String metric,Machine learning | Conference | D12-1 |
Citations | PageRank | References |
73 | 3.13 | 27 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Bo Han | 1 | 593 | 29.85 |
Paul Cook | 2 | 345 | 14.35 |
Timothy Baldwin | 3 | 426 | 20.64 |