We are just announcing the workshop this year will be held at COLING! We look forward to seeing you!
WNUT workshop focuses on Natural Language Processing applied to noisy user-generated text, such as that found in social media, web forums, online reviews, clinic records and language learner essays. This year, there will be two shared tasks: 1) Geolocation Prediction in Twitter and 2) Named Entity Recognition in Twitter.
We seek submissions of both long and short papers on original and unpublished work (same page limit as COLING main conference). 1-page abstracts on work-in-progress or work published elsewhere are also welcome and will *not* be included in the conference proceedings.
All accepted submissions will be presented as posters. Additionally, selected submissions will be presented orally. The share-task participants are also encouraged (but not required) to submit system description papers and present posters; the top systems will be invited (but not required) to present orally.
Topics of interest include but are not limited to:
NLP Preprocessing of Noisy Text
Part of speech tagging
Named entity tagging, including a wide range of categories, e.g. product names
Chunking of user-generated text
Text Normalization and Error Correction
Normalizing noisy text for downstream tasks and for human readability
Error detection and correction
Paraphrase extraction and detection in noisy text
User prediction, e.g. geolocation, gender, age, etc
Bilingual translation of noisy text
Multilingual NLP in noisy text
Colloquial language, e.g. idiom detection
Domain adaptation to user-generated text
All submissions should conform to COLING 2016 style guidelines. Long and short paper submissions must be anonymized. Abstract submissions should include author information (and where the work was published in a footnote on front page, if applicable). Please submit your papers here (the link will become available later).