[Corpora-List] [Hybrid event] AMORE Mini-workshop on Referential Information in Deep Learning Models

Gemma Boleda gemma.boleda at upf.edu
Mon Apr 4 17:22:30 CEST 2022


AMORE Mini-workshop on Referential Information in Deep Learning Models <https://www.upf.edu/web/amore/home/-/asset_publisher/zT3lPdngMqBo/content/id/256963087/maximized> Open to everyone who's interested! Hybrid event, see Zoom link below.

-

When: Monday 11 April, 15:00h - 17:00h

-

Where: 55.309 (UPF - Tānger Building

<https://www.upf.edu/en/web/campus/tanger>; access through Roc Boronat

Building <https://www.upf.edu/web/campus/roc-boronat>, Carrer Roc

Boronat 138)

-

*Zoom link*: https://upf-edu.zoom.us/j/92979825202

-

Schedule (see talk abstracts below):

-

15:00 - 16:00: Raquel Fernāndez

<https://staff.fnwi.uva.nl/r.fernandezrovira/> (ILLC - University of

Amsterdam)

-

16:00 - 17:00: Anna Rogers <https://annargrs.github.io> (University

of Copenhagen)

-

17:00: Coffee break

Raquel Fernāndez - Efficient Language Production Strategies in Visually Grounded Dialogue

Speakers are thought to use efficient information transmission strategies for effective communication. For example, the Uniform Information Density principle states that speakers plan their utterances to reduce fluctuations in the density of the information transmitted. Previous work analysing this principle in dialogue has failed to take into account how the information content of utterances varies as a function of the available discourse context, and has completely ignored the role of extralinguistic information. In this talk, I will present work that tests whether and within which contextual units this principle holds in visually grounded task-oriented dialogues. We analyse production strategies in these dialogues combining information-theoretic measures with probability estimates and visuo-linguistic alignment scores obtained from transformer-based language models and multimodal models. Our findings show that efficient strategies are at play in dialogue when we zoom in on topically and referentially coherent contextual units. Beside providing empirical insights on human production strategies, our studies can inform the development of more human-like natural language generation models. Anna Rogers - Challenges in Defining and Testing Machine Verbal Reasoning Skills

Natural language understanding is a quickly growing field, both in terms of modeling and data work. However, there is little agreement on what specific reasoning "skills" the models are supposed to learn, which is why many resource descriptions and error analysis sections rely on ad-hoc categories. This talk presents a taxonomy of verbal reasoning skills for future resource and model analysis work, based on the findings of a large-scale survey of current resources for reading comprehension and question answering. I will also discuss the key challenges in model evaluation and collecting data for training/testing specific "skills", as well as some proposed solutions. -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: text/html Size: 5108 bytes Desc: not available URL: <https://mailman.uib.no/public/corpora/attachments/20220404/6090c224/attachment.txt>



More information about the Corpora mailing list