2022 The 8th Workshop on Noisy User-generated Text (W-NUT)
Oct 16, 2022 — collocated with COLING 2022.
The WNUT workshop focuses on Natural Language Processing applied to noisy user-generated text, such as that found in social media, online reviews, crowdsourced data, web forums, clinical records and language learner essays. The workshop has accepted 25 papers (short and long). See the program schedule for further details.
News: best paper award, sponsored by Megagon Labs.
Workshop Organizers
|
|
|
|
Wei Xu Assistant Professor Georgia Institute of Technology |
Afshin Rahimi Lecturer University of Queensland |
Alan Ritter Associate Professor Georgia Institute of Technology |
Tim
Baldwin Professor MBZUAI and University of Melbourne |
Invited Speakers
Important Dates
- Submission Deadline:
August 19, 2022 August 24, 2022 (anytime on earth; dual-submission allowed)
- Reviews Due: September 4, 2022
- Acceptance Notification:
September 7, 2022 September 8, 2022
- Camera-Ready Deadline: September 14, 2022
- Workshop Day: October 16, 2022
Call for Papers
We seek submissions of long and short papers
on
original and unpublished work (same page limit as the COLING 2022 main conference). All accepted submissions will be presented as talks and/or posters at the workshop virtually, following the COLING 2022 main conference.
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
- Parsing
- Text Normalization and Error Correction
- Normalizing noisy text for downstream tasks and for human readability
- Error detection and correction
- Robustness to Noise, both Natural and Adversarial
- Multilingual NLP in noisy text
- Machine Translation of Noisy Text
- Sentiment analysis
- Crowdsourcing of text data
- User prediction, e.g. gender, age, etc
- Stylistics, e.g. formality, politeness, etc
- Colloquial language, e.g. code-switching, idiom detection
- Bilingual translation of the noisy text
- Paraphrase identification and semantic similarity of short text or noisy text
- Information extraction from noisy text
- Domain adaptation to user-generated text
- Geolocation prediction
- Global and regional trend detection and event extraction
- Detecting rumors, contradictory information, sarcasm and humor on social media
- Fairness and bias in NLP models, when applied to noisy inputs
- Temporal aspects of user-generated content (resolving time expressions, concept drift, diachronic analyses, etc...)
All submissions should conform
to
COLING 2022 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 the front page, if applicable). Please submit your
papers via
SoftConf.
Double Submission Policy: Papers that have been or will be submitted to other meetings or publications must indicate at submission time. Authors of a paper accepted for presentation must notify the workshop organizers by the camera-ready deadline as to whether the paper will be presented or withdrawn.
Program Committee