Abstract
We present a suite of 12 datasets for evaluating POS taggers across varieties of English to enable researchers to evaluate the robustness of their models. The suite includes three new datasets, sampled from lyrics from black American hip-hop artists, southeastern American Twitter, and the subtitles from the TV series The Wire. We present an example eval- uation of an off-the-shelf POS tagger across these datasets.
Originalsprog | Engelsk |
---|---|
Titel | Proceedings of the 25th International Conference Companion on World Wide Web |
Antal sider | 4 |
Forlag | International World Wide Web Conferences Steering Committee |
Publikationsdato | 11 apr. 2016 |
Sider | 615-618 |
ISBN (Trykt) | 978-1-4503-4144-8 |
DOI | |
Status | Udgivet - 11 apr. 2016 |
Begivenhed | 25th International World Wide Web Conference - Montreal, Canada Varighed: 11 apr. 2016 → 15 apr. 2016 Konferencens nummer: 25 |
Konference
Konference | 25th International World Wide Web Conference |
---|---|
Nummer | 25 |
Land/Område | Canada |
By | Montreal |
Periode | 11/04/2016 → 15/04/2016 |