2017/07/17 by Rob van der Goot, Barbara Plank, van der Goot, Rob +3
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Speech and dialogue systems #Topic Modeling #cs.CL
paper · pdf · doi:10.48550/arxiv.1707.05116
In WNUT 2017
arxiv created 2017/07/17 · openalex publication_date 2017/07/17 · arxiv updated 2017/07/18 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Does normalization help Part-of-Speech (POS) tagging accuracy on noisy, non-canonical data? To the best of our knowledge, little is known on the actual impact of normalization in a real-world scenario, where gold error detection is not available. We investigate the effect of automatic normalization on POS tagging of tweets. We also compare normalization to strategies that leverage large amounts of unlabeled data kept in its raw form. Our results show that normalization helps, but does not add consistently beyond just word embedding layer initialization. The latter approach yields a tagging model that is competitive with a Twitter state-of-the-art tagger.