|
We are pleased to announce the GeCKo (Integrating Generic and Contextual Knowledge) symposium, which will take place on May 18th, in Barcelona (Spain)!
Integrating generic and contextual knowledge remains a challenging task in Computational Linguistics and interfacing fields. While current data-driven models excel in capturing broad regularities, they can fail to apply this information to specific situations. For the GeCKo symposium we seek contributions dealing with this issue, at the crossroads of Computational Linguistics, Machine Learning, Linguistics, and Cognitive Science; including areas such as Language and Vision, and Machine Translation.
INVITED SPEAKERS
Aishwarya Agrawal, DeepMind London
Raquel Fernandez, University of Amsterdam
Aurelie Herbelot, University of Trento
Shalom Lappin, University of Gothenburg
Tomas Mikolov, Facebook AI Research
Rico Sennrich, University of Zurich
DATES
Submission due: February 7th 2020, 11:59PM UTC-12:00 ("anywhere on Earth")
Notification of acceptance: March 13th 2020
GeCKo symposium: May 18th 2020
CALL FOR CONTRIBUTIONS
For both humans and computational models, it is essential to be able to abstract away from specific instances to broader categories, e.g. to build a generic concept for "bird" from instances of birds. But modelling specific situations is equally essential; for instance to be able to understand the sentence "that bird is about to peck you" and react accordingly. Current data-driven models excel at distilling generic knowledge acquired over time, such as knowledge reflected by which words or objects tend to co-occur. However, they can still struggle with specific situations, which require fast recognition of individual elements, such as entities, events, and relationships, and the ability to reason about them. In the literature, the relation between generic and contextual knowledge surfaces in dichotomies such as:
- lexical/conceptual/generic vs. contextual(ized)/grounded/situated/referential/utterance-specific information;
- category/type/kind vs. instance/token;
- semantics vs. pragmatics;
- semantic vs. episodic memory;
- slow vs. fast learning.
The GeCKo symposium seeks to 1) understand the issues involved in the integration of generic and situation-specific information in Computational Linguistics, across applications and research areas; 2) identify ways forward; and 3) cross-fertilize Computational Linguistics with Machine Learning, Linguistics, and Cognitive Science researchers working at this junction.
The GeCKo symposium will feature talks by invited speakers, contributed talks, as well as a poster session preceded by lightning talks. We seek contributions of published work as well as unpublished research, of the following, non-exclusive types:
- Analysis: what kind of situation-specific information can current models capture; what can’t they?
- Modelling: models and/or tasks aimed at integrating generic and situation-specific information in any area related to CL/NLP.
- Cross-fertilizing: how can computational models of language integrate current findings in Linguistics, Cognitive Science, and Machine Learning about generic vs. situation-specific information? How can our results inform those fields in turn?
- Position papers and surveys outlining the issues involved and ways forward.
SUBMISSION INFORMATION
The GeCKo symposium invites the submission of two kinds of contributions:
- Published research: contributions published in other venues — the submission form will simply ask for a link to the publication
- Unpublished research: abstracts presenting unpublished work, including work under review elsewhere, or ongoing efforts — anonymous, 1 page plus references.
Accepted submissions will be allocated to either poster or oral presentation; posters will be introduced by lightning talks. There will be no archival GeCKo proceedings.
The submission form will be made available at: https://sites.google.com/view/gecko2020
ORGANIZERS
Laura Aina, Gemma Boleda, Thomas Brochhagen, Desmond Elliott, Carina Silberer, Ionut-Teodor Sorodoc, Matthijs Westera, Sina Zarrieß.
Please feel free to get in touch with us at [email protected].
|
