Un articolo de Il Mattino che parla del sistema di generazione e riconoscimento di metafore METCL, sviluppato Gian Luca Pozzato e Stefano Zoia, e sarà presentato alla 34th International Joint Conference on Artificial Intelligence, a Montreal #IJCAI2025 :

Paper: The Delta of Thought: Channeling Rivers of Commonsense Knowledge in the Sea
of Metaphorical Interpretations: https://www.ciitlab.org/IJCAI_25_Lieto_Pozzato_Zoia_.pdf

An article on il Mattino on the METCL metaphor generation and recognition system developed with @Gian Luca Pozzato and Stefano Zoia, and that will be presented at the 34th International Joint Conference on Artificial Intelligence, #IJCAI2025, in Montreal

Paper: The Delta of Thought: Channeling Rivers of Commonsense Knowledge in the Sea
of Metaphorical Interpretations: https://www.ciitlab.org/IJCAI_25_Lieto_Pozzato_Zoia_.pdf

#IJCAI2025 #computationalcreativity #commonsensereasoning #metaphors #AiResearch #AI

📚 Publication News from CIIT Lab @ IJCAI 2025 Ijcai:
Last week, the paper “The Delta of Though: Channeling Rivers of Commonsense Knowledge in the Sea of Metaphorical Interpretations” by Antonio Lieto, Gian Luca Pozzato and Stefano Zoia has been accepted at the prestigious International Joint Conference on Artificial Intelligence (IJCAI 2025) that will be held in Montreal next August (16-22).

📝 Title: The Delta of Though: Channeling Rivers of Commonsense Knowledge in the Sea of Metaphorical Interpretations

🔍 Abstract:
We propose a system called METCL (Metaphor Elaboration in Typicality-Based Compositional Logic) able to generate and identify metaphors by using the TCL reasoning framework, specialized in human-like commonsense concept combination. We show thatMETCL is able to improve both state of-the-art Large Language Models (e.g DeepSeek-R1, GPT-4o, Qwen2.5-Max) and symbolic ones in the task of metaphor identification. Additionally,
we show how the metaphors generated by METCL are generally well accepted by human subjects.
The obtained results are encouraging and pave the way to research in automatic metaphor generation and comprehension based on the assumption that metaphors interpretation can be partially regarded as a categorization problem relying on generative commonsense concept combination.

#ai #commonsensereasoning #conceptcombination, #metaphor #cogsci #computationalcreativity

Link to the paper: https://lnkd.in/dqVpz74E

@cognition @academicchatter

Check out the paper "Two semantic interpretations of probabilities in description logics of typicality" published in Logic Journal of IGPL (Oxford University Press) that describes a novel probabilistic description logics that, like TCL (https://antoniolieto.net/tcl_logic.html) allows to deal with the problem of compositionality of typical representations but, unlike TCL https://doi.org/10.1080/0952813X.2019.1672799, doesn't use an epistemic interpretation. Link: https://doi.org/10.1093/jigpal/jzae086

#AI #commonsensereasoning

A personal & relevant tribute to the life and work of #DougLenat, who tried, and largely failed, to bring #CommonSenseReasoning to #AI. I used Cyc in some projects in the 90’s. HT @garymarcus

https://open.substack.com/pub/garymarcus/p/doug-lenat-1950-2023?r=aewhd&utm_medium=ios&utm_campaign=post

Presenting the #affectivecomputing & recommendation system DEGARI (Dynamic #Emotion Generator And ReclassIfier) in the SPICE project in Haifa.

DEGARI employs the TCL reasoning framework (https://www.antoniolieto.net/tcl_logic.html) to generate complex emotions and uses them to classify and to recommend museum items

References:

[1] https://www.sciencedirect.com/science/article/pii/S0950705121004299
[2] DEGARI 2.0 https://doi.org/10.1016/j.cogsys.2022.10.001

#emotionreasoning #artificialintelligence #explainableai #commonsensereasoning