Room: A008 (in front of LORIA’s reception)
9h-9h15: Opening [slides]
9h15-10h15: Invited talk – Stergos Afantenos (IRIT)
Title: Analogies: a brief attempt at understanding what they are and an even briefer one at detecting analogies between pairs of sentences.
Abstract: Analogies have been preoccupying thinkers at least since the post-mycenaean period of the Greeks (e.g. Euclid, Theon, Aristotle, etc). More recently they have been characterized as being at the core of cognition (Hofstadter 2001, Hofstadter and Sanders 2013). In this talk we will attempt to briefly shed some light on the various points of view via which analogies have been approached, without being of course exhaustive. For the second part of this presentation we will retain the classical approach of analogies as proportions between four terms a:b::c:d (a is to b as c is to d) where a, b, c and d are sentences. We will present a series of experiments trying to understand whether the classical postulates hold for analogies between sentences, focusing mostly on the central permutation. We will also explore how well recurrent neural networks and transformer based ones are capable of detecting analogies between sentences.
10h15-10h40: Interactions Between Knowledge Graph-Related Tasks and Analogical Reasoning: A Discussion (Pierre Monnin and Miguel Couceiro) [paper] [slides]
10h40-11h00: Coffee break
11h00-11h25: Sentence Analogies for Text Morphing (Zhicheng Pan, Xinbo Zhao and Yves Lepage) [paper]
11h30-11h55: Transferring Learned Models of Morphological Analogy (Esteban Marquer, Pierre-Alexandre Murena and Miguel Couceiro) [paper] [slides]
12h00-12h25: Extraction of Analogies Between Sentences on the Level of Syntax Using Parse Trees (Yifei Zhou, Rashel Fam and Yves Lepage) [paper]
12h30-12h55: CoAT-APC: When Analogical Proportion-based Classification Meets Case-based Prediction (Fadi Badra and Marie-Jeanne Lesot) [paper]
13h00-14h30: Lunch break
14h30-15h30: Invited talk – Claire Gardent (CNRS, LORIA)
Title: Neural Approaches to Analogies [slides]
Abstract: Over the last decade, neural methods have been proposed to process analogies i.e., quadruplets of the form A:B :: C:D such that the relation that holds between A and B also hold between C and D. In this talk, I will review some of this work focusing on the models used, on the representations proposed and on the motivations underlying the different proposals. The talk will focus mostly on neural approaches to analogy for text, structured data and images.
15h30-15h55: An analogy based framework for patient-stay identification in healthcare (Safa Alsaidi, Miguel Couceiro, Esteban Marquer, Sophie Quennelle, Anita Burgun, Nicolas Garcelon and Adrien Coulet) [paper]
16h00-16h25: Towards efficient scoring of student-generated long-form analogies in STEM (Thilini Wijesiriwardene, Ruwan Wickramarachchi, Valerie L. Shalin and Amit P. Sheth) [paper]
16h30-17h00: Coffee break
17h00-18h00: Invited talk – Dave Raggett (W3C/ERCIM)
Title: The application of qualitative metadata to analogical reasoning [paper] [slides]
Abstract: Analogical reasoning can be used for plausible inferences based upon direct similarities or structural mappings involving properties and relationships. This can be implemented on top of a combination of symbolic knowledge plus sub-symbolic qualitative metadata, with matching based upon structural or causal similarities, and noticing interesting differences, in essence, abstracting from similarities and dissimilarities, and will be applied to examples of the form “A is to B as C is to ?X”. A further challenge is to support the use of literal and figurative analogies in natural language, e.g. comparing life to the wheel of fortune, when you want to highlight the role of chance. An easy to use syntax will be presented for expressing knowledge, along with a web-based proof of concept demonstrator, and a unifying cognitive architecture for human-like AI. This builds upon work by Alan Colins on plausible reasoning and Dedre Gentner on analogies.
18h00-18h30: Discussion & Conclusion
