Marta Ruiz Costa-Jussa
2021-04-19 13:55:21 UTC
ACL-IJCNLP 3rd Workshop on Gender Bias for Natural Language Processing
http://genderbiasnlp.talp.cat
5-6 August, Bangkok, Thailand
Gender and other demographic biases (e.g. race, nationality, religion) in
machine-learned models are of increasing interest to the scientific
community and industry. Models of natural language are highly affected by
such biases, which are present in widely used products and can lead to poor
user experiences. There is a growing body of research into improved
representations of gender in NLP models. Popular approaches include
building and using balanced training and evaluation datasets (e.g. Reddy &
Knight, 2016, Webster et al., 2018, Maadan et al., 2018), and changing the
learning algorithms themselves (e.g. Bolukbasi et al., 2016, Chiappa et
al., 2018). While these approaches show promising results, there is more to
do to solve identified and future bias issues. In order to make progress as
a field, we need to create widespread awareness of bias and a consensus on
how to work against it, for instance by developing standard tasks and
metrics. Our workshop provides a forum to achieve this goal. Our workshop
follows up two successful previous editions of the Workshop collocated with
ACL 2019 and COLING 2020, respectively. Following the successful
introduction of bias statements at GeBNLP 2020, we continue to require bias
statements in this yearâs workshops and will again ask the program
committee to engage with the bias statements in the papers they review.
This helps to make clear (a) what system behaviors are considered as bias
in the work, and (b) why those behaviors are harmful, in what ways, and to
whom. We encourage authors to engage with definitions of bias and other
relevant concepts such as prejudice, harm, discrimination from outside NLP,
especially from social sciences and normative ethics, in this statement and
in their work in general. Also, we will be keeping pushing the integration
of several communities such as social sciences as well as a wider
representation of approaches dealing with bias.
Topics of interest
We invite submissions of technical work exploring the detection,
measurement, and mediation of gender bias in NLP models and applications.
Other important topics are the creation of datasets exploring demographics
such as metrics to identify and assess relevant biases or focusing on
fairness in NLP systems. Finally, the workshop is also open to
non-technical work addressing sociological perspectives, and we strongly
encourage critical reflections on the sources and implications of bias
throughout all types of work.
Paper Submission Information
Submissions will be accepted as short papers (4-6 pages) and as long papers
(8-10 pages), plus additional pages for references, following the
ACL-IJCNLP 2021 guidelines. Supplementary material can be added, but should
not be central to the argument of the paper. Blind submission is required.
Each paper should include a statement that explicitly defines (a) what
system behaviors are considered as bias in the work and (b) why those
behaviors are harmful, in what ways, and to whom (cf. Blodgett et al. (2020)
<https://arxiv.org/abs/2005.14050>). More information on this requirement,
which was successfully introduced at GeBNLP 2020, can be found on the workshop
website
<https://genderbiasnlp.talp.cat/gebnlp2020/how-to-write-a-bias-statement/>.
We also encourage authors to engage with definitions of bias and other
relevant concepts such as prejudice, harm, discrimination from outside NLP,
especially from social sciences and normative ethics, in this statement and
in their work in general.
Important dates
April 26, 2021: Workshop Paper Due Date
May 28, 2021: Notification of Acceptance
June 7, 2021: Camera-ready papers due
August 5-6, 2021: Workshop Dates
Keynote
Sasha Luccioni, MILA, Canada
Programme Committee
Svetlana Kiritchenko, National Council Canada, Canada
Sharid Loáiciga, University of Gothenburg, Sweden
Kaiji Lu, Carnegie Mellon University, US
Marta Recasens, Google, US
Bonnie Webber, University of Edinburgh, UK
Ben Hachey, Harrison.ai Australia
Mercedes GarcÃa MartÃnez, Pangeanic, Spain
Sonja Schmer-Galunder, Smart Information Flow Technologies, US
Matthias Gallé, NAVER LABS Europe, France
Sverker Sikström, Lund University, Sweden
Dirk Hovy, Bocconi University, Italy
Carla Perez Almendros, Cardiff University, UK
Jenny Björklund, Uppsala University
Su Lin Blodgett, UMass Amherst
Will Radford, Canvas, Australia
Organizers
Marta R. Costa-jussà , Universitat PolitÚcnica de Catalunya, Barcelona
Hila Gonen, Amazon
Christian Hardmeier, IT University of Copenhagen/Uppsala University
Kellie Webster, Google AI Language, New York
Contact persons
Marta R. Costa-jussà : marta (dot) ruiz (at) upc (dot) edu
http://genderbiasnlp.talp.cat
5-6 August, Bangkok, Thailand
Gender and other demographic biases (e.g. race, nationality, religion) in
machine-learned models are of increasing interest to the scientific
community and industry. Models of natural language are highly affected by
such biases, which are present in widely used products and can lead to poor
user experiences. There is a growing body of research into improved
representations of gender in NLP models. Popular approaches include
building and using balanced training and evaluation datasets (e.g. Reddy &
Knight, 2016, Webster et al., 2018, Maadan et al., 2018), and changing the
learning algorithms themselves (e.g. Bolukbasi et al., 2016, Chiappa et
al., 2018). While these approaches show promising results, there is more to
do to solve identified and future bias issues. In order to make progress as
a field, we need to create widespread awareness of bias and a consensus on
how to work against it, for instance by developing standard tasks and
metrics. Our workshop provides a forum to achieve this goal. Our workshop
follows up two successful previous editions of the Workshop collocated with
ACL 2019 and COLING 2020, respectively. Following the successful
introduction of bias statements at GeBNLP 2020, we continue to require bias
statements in this yearâs workshops and will again ask the program
committee to engage with the bias statements in the papers they review.
This helps to make clear (a) what system behaviors are considered as bias
in the work, and (b) why those behaviors are harmful, in what ways, and to
whom. We encourage authors to engage with definitions of bias and other
relevant concepts such as prejudice, harm, discrimination from outside NLP,
especially from social sciences and normative ethics, in this statement and
in their work in general. Also, we will be keeping pushing the integration
of several communities such as social sciences as well as a wider
representation of approaches dealing with bias.
Topics of interest
We invite submissions of technical work exploring the detection,
measurement, and mediation of gender bias in NLP models and applications.
Other important topics are the creation of datasets exploring demographics
such as metrics to identify and assess relevant biases or focusing on
fairness in NLP systems. Finally, the workshop is also open to
non-technical work addressing sociological perspectives, and we strongly
encourage critical reflections on the sources and implications of bias
throughout all types of work.
Paper Submission Information
Submissions will be accepted as short papers (4-6 pages) and as long papers
(8-10 pages), plus additional pages for references, following the
ACL-IJCNLP 2021 guidelines. Supplementary material can be added, but should
not be central to the argument of the paper. Blind submission is required.
Each paper should include a statement that explicitly defines (a) what
system behaviors are considered as bias in the work and (b) why those
behaviors are harmful, in what ways, and to whom (cf. Blodgett et al. (2020)
<https://arxiv.org/abs/2005.14050>). More information on this requirement,
which was successfully introduced at GeBNLP 2020, can be found on the workshop
website
<https://genderbiasnlp.talp.cat/gebnlp2020/how-to-write-a-bias-statement/>.
We also encourage authors to engage with definitions of bias and other
relevant concepts such as prejudice, harm, discrimination from outside NLP,
especially from social sciences and normative ethics, in this statement and
in their work in general.
Important dates
April 26, 2021: Workshop Paper Due Date
May 28, 2021: Notification of Acceptance
June 7, 2021: Camera-ready papers due
August 5-6, 2021: Workshop Dates
Keynote
Sasha Luccioni, MILA, Canada
Programme Committee
Svetlana Kiritchenko, National Council Canada, Canada
Sharid Loáiciga, University of Gothenburg, Sweden
Kaiji Lu, Carnegie Mellon University, US
Marta Recasens, Google, US
Bonnie Webber, University of Edinburgh, UK
Ben Hachey, Harrison.ai Australia
Mercedes GarcÃa MartÃnez, Pangeanic, Spain
Sonja Schmer-Galunder, Smart Information Flow Technologies, US
Matthias Gallé, NAVER LABS Europe, France
Sverker Sikström, Lund University, Sweden
Dirk Hovy, Bocconi University, Italy
Carla Perez Almendros, Cardiff University, UK
Jenny Björklund, Uppsala University
Su Lin Blodgett, UMass Amherst
Will Radford, Canvas, Australia
Organizers
Marta R. Costa-jussà , Universitat PolitÚcnica de Catalunya, Barcelona
Hila Gonen, Amazon
Christian Hardmeier, IT University of Copenhagen/Uppsala University
Kellie Webster, Google AI Language, New York
Contact persons
Marta R. Costa-jussà : marta (dot) ruiz (at) upc (dot) edu