Call for papers for the first Workshop on SemiParametric Methods in NLP:
Deadlines extended: In order to accomodate more submissions, we’ve extended the submission deadlines by a few days.
Large parametric language models have achieved dramatic empirical success across many applications. However, these models lack several desirable properties such as explainability (providing provenance), privacy (ability to remove knowledge from the model), robust controllability, and debuggability. On the other hand, nonparametric models provide many of these features by design such as provenance, ability to incorporate/remove information. However, these models often suffer from weaker empirical performance as compared to deep parametric models.
Recently, many works have independently proposed a middle ground that combines a parametric model (that encodes logic) with a nonparametric model (that retrieves knowledge) in various areas from question answering over natural languages to complex reasoning over knowledge bases to even protein structure predictions. Given the increasingly promising results on various tasks of such semiparametric model, we believe this area is ripe for targeted investigation on understanding efficiency, generalization, limitations, widening its applicability, etc. As a result, we want to host a workshop on this topic.
This workshop aims to invite researchers to share their latest work in designing and understanding semiparametric models. We will welcome papers / work-in-progress on several topics (but not limited to):
- Understanding properties and capabilities
- Expressivity of semiparametric models
- Generalization in low resource settings
- Quick adaptation to newly emerging phenomena/temporally aware
- Right to be forgotten/ GDPR /Privacy
- Interpretability, explainability, and controllability
- Models that do explicit reasoning with non-parametric components (than implicitly doing in parameters)
- Case-based reasoning
- Episodic control
- On-the-fly Neuro-symbolic Reasoning and Neural Theorem Proving
- Organizing non-parametric components for efficient use in semi-parametric models
- Hierarchies/DAGs
- Incremental Data structures
- Applications to existing/new tasks
- QA and Semantic Parsing
- Structured Prediction
- Machine Translation
- Recommender systems
- Information Retrieval and Extraction
- New applications
- Analysis and limitations of current models
- Faithfulness to the retrieved information
- How much retrieval is sufficient?
- Efficiency trade-offs
Important Dates
We will have an archival track as well as a non-archival track. Archival track submissions either go through a standard double-blind review process, or can be submitted with ARR reviews. The non-archival track seeks recently published work—it does not need to be anonymized and will not go through the review process. The submission should clearly indicate the original venue and will be accepted if the commitee think the work will benefit from exposure to the audience of the workshop. Non-archival papers will not be included in the workshop proceedings.
(All AoE)
- Submission deadline (for papers requiring peer review): March 3rd, 2022
- Submission deadline (with ARR reviews): March 24th, 2022
- Submission deadline (Non-archival): March 24th, 2022
- Notification of acceptance: March 26th, 2022
- Camera-ready paper deadline: April 10th, 2022
- Workshop date: May 27th, 2022