Until recently, the dominant paradigm in natural language processing (and other areas of artificial intelligence) has been to resolve observed label disagreement into a single “ground truth” or “gold standard” via aggregation, adjudication, or statistical means. However, in recent years, the field has increasingly focused on subjective tasks, such as abuse detection or quality estimation, in which multiple points of view may be equally valid, and a unique ‘ground truth’ label may not exist (Plank, 2022). At the same time, as concerns have been raised about bias and fairness in AI, it has become increasingly apparent that an approach which assumes a single “ground truth” can erase minority voices.
Strong perspectivism in NLP (Cabitza et al., 2023) pursues the spirit of recent initiatives such as Data Statements (Bender and Friedman, 2018), extending their scope to the full NLP pipeline, including the aspects related to modelling, evaluation and explanation.
In line with with the first and second editions, the NLPerspectives (Perspectivist Approaches to Disagreement in NLP) workshop will explore current and ongoing work on: the collection and labelling of non-aggregated datasets; and approaches to modelling and including these perspectives, as well as evaluation and applications of multi-perspective Machine Learning models. We also welcome opinion pieces and literature reviews, e.g., in the context of fairness and inclusion.
A key outcome of this second edition will be to build on the work begun at https://pdai.info/ to create a repository of perspectivist datasets with non-aggregated labels for use by researchers in perspectivist NLP modelling.
Authors are, therefore, invited to share their LRs (data, tools, services, etc.) and provide essential information about resources (i.e., also technologies, standards, evaluation kits, etc.) that have been used for the work or are a result of their research. In addition, authors will be required to adhere to ethical research policies on AI and may include an ethics statement in their papers.
The NLPerspectives workshop will be co-located with the 14th edition of LREC-COLING 2024 in Torino, Italy, in May 20-25, 2024 and online.
Submissions
The papers should be submitted as a PDF document, conforming to the formatting guidelines provided in the call for papers of LREC-COLING conference: authors-kit
We accept three types of submissions:
- Regular research papers;
- Non-archival submissions: like research papers, but will not be included in the proceedings;
- Research communications: 4-page abstracts summarising relevant research published elsewhere.
Long papers are allowed up to eight (8) pages maximum and short papers are allowed up to four (4) pages, excluding any number of additional pages for references, ethical consideration, conflict-of-interest, as well as data and code availability statements.
Submissions should be sent in electronic forms, using the Softconf START conference management system at this URL:
https://softconf.com/lrec-coling2024/nlperspectives2024/user/
Topics
We invite original research papers from a wide range of topics, including but not limited to:
- Non-aggregated data collection and annotation frameworks
- Descriptions of corpora collected under the perspectivist paradigm
- Multi-perspective Modelling and Machine Learning
- Evaluation of multi-perspective models/ models of disagreement
- Multi-perspective disagreement as applied to NLP evaluation
- Fairness and inclusive modelling
- Perspectivist approaches for social good
- Applications of multi-perspective modelling
- Computing with (dis)agreement
- Perspectivist Natural Language Generation
- Foundational aspects of perspectivism
- Opinion pieces and reviews on perspectivist approaches to NLP
Submissions are open to all, and are to be submitted anonymously (and must conform to the instructions for double-blind review). All papers will be refereed through a double-blind peer review process by at least three reviewers, with final acceptance decisions made by the workshop organisers. Scientific papers will be evaluated based on relevance, significance of contribution, impact, technical quality, scholarship, and quality of presentation.
More information about the submission, publication of proceedings and date of the workshop will be provided soon. We are seeking sponsors in order to provide financial support for conference registration, travel, and accommodation for participants.
Attendance
At least one author of each accepted paper is required to participate in the conference and present the work, in-person or online.
Important Dates
- Friday
February 23EXTENDED March 1, 2024: Paper submission - Friday March 28, 2024: Notification of acceptance
- Friday April 8, 2024: Camera-ready papers due
- Tuesday May 21, 2024: Workshop
Workshop organisers:
Gavin Abercrombie, Heriot-Watt University
Valerio Basile, University of Turin
Davide Bernardi, Amazon Alexa
Shiran Dudy, University of Colorado, Boulder
Simona Frenda, University of Turin
Lucy Havens, University of Edinburgh
Sara Tonelli, Fondazione Bruno Kessler