Many recent performance improvements in NLP have come at the cost of understanding
of the systems. How do we assess what representations and computations models learn?
How do we formalize desirable properties of interpretable models, and measure the
extent to which existing models achieve them? How can we build models that better
encode these properties? What can new or existing tools tell us about these
systems’ inductive biases?
The goal of this workshop is to bring together researchers focused on interpreting
and explaining NLP models by taking inspiration from fields such as machine learning,
psychology, linguistics, and neuroscience. We hope the workshop will serve as an
interdisciplinary meetup that allows for cross-collaboration.
Topics of interest include, but are not limited to:
* Applying analysis techniques from neuroscience to analyze
high-dimensional vector representations in artificial neural networks;
* Analyzing the network’s response to strategically chosen input in order
to infer the linguistic generalizations that the network has acquired;
* Examining network performance on simplified or formal languages;
* Mechanistic interpretability, reverse engineering approaches to understanding
particular properties of neural models;
* Proposing modifications to neural architectures that increase their
interpretability;
* Testing whether interpretable information can be decoded from
intermediate representations;
* Explaining specific model predictions made by neural networks;
* Generating and evaluating the quality of adversarial examples in NLP;
* Developing open-source tools for analyzing neural networks in NLP;
* Evaluating the analysis results: how do we know that the analysis is
valid?
BlackboxNLP 2023 is the sixth BlackboxNLP workshop. The programme and
proceedings of the previous editions can be found on the workshop website.
Submissions
-----------------
We call for two types of papers:
1) Archival papers. These are papers reporting on completed, original and
unpublished research, with a maximum length of 8 pages + references. Papers
shorter than this maximum are also welcome. Accepted papers are expected to
be presented at the workshop and will be published in the workshop
proceedings. They should report on obtained results rather than intended
work. These papers will undergo double-blind peer-review, and should thus
be anonymized.
2) Extended abstracts. These may report on work in progress or may be cross
submissions that have already appeared in a non-NLP venue. The extended
abstracts are of maximum 2 pages + references. These submissions are
non-archival in order to allow submission to another venue. The selection
will not be based on a double-blind review and thus submissions of this
type need not be anonymized.
Submissions should follow the official EMNLP 2023 style guidelines. The
submission site is:
https://www.softconf.com/emnlp2023/blackboxnlp2023/
Contact
---------------------
Please contact the organizers at blackboxnlp@googlegroups.com for any questions.
Important dates
---------------------
September 1, 2023 – Submission deadline.
October 6, 2023 – Notification of acceptance.
October 18, 2023 – Camera-ready papers due.
December 7, 2023 – Workshop.
Note: All deadlines are 11:59PM UTC-12:00, 'anywhere on earth'.