Abralin ao vivo

« previous post | next post »

[This event has been postponed to Saturday 6/13/2020 in accordance with the call to #ShutDownSTEM]

The Brazilian Linguistics Association has been sponsoring a series of on-line lectures — Abralin ao vivo:

The coronavirus pandemic has reshaped many of our academic practices. At this time, social distance is an important and necessary measure. However, the exchange of ideas within the linguistic community has to be maintained. With this in mind, the Brazilian Linguistics Association, Abralin, in cooperation with CIPL – Comité International Permanent des Linguistes, ALFAL – Asociación de Lingüística y Filología de América Latina, SAEL – Sociedad Argentina de Estudios Lingüísticos, ALAB – Associação de Linguística Aplicada do Brasil, AILA – Association Internationale de Linguistique Appliquée, LSA – Linguistic Society of America, LAGB – Linguistics Association of Great Britain, SLE – Societas Linguistica Europaea, ALS – Australian Linguistic Society and BAAL – British Association for Applied Linguistics is organizing a virtual event: Abralin ao Vivo – Linguists Online. The event is designed to give students and researchers free access to state-of-the-art discussions on the most diverse topics related to the study of human language.

My turn is coming on Wednesday 6/13 at 17:00 BRT (16:00 EDT):

The abstract:

We infer a lot from the way someone talks: personal characteristics like age, gender, background, personality; contextual characteristics like mood and attitude towards the interaction; physiological characteristics like fatigue or intoxication. Many clinical diagnostic categories have symptoms that are manifest in spoken interaction: autism spectrum disorder, neurodegenerative disorders, schizophrenia, and so on.⠀

The development of modern speech and language technology makes it possible to create automated methods for diagnostic screening or monitoring. More important is the fact that these diagnostic categories are phenotypically diverse, representing (sometimes apparently discontinuous) regions of complex multidimensional behavioral spaces. We can hope that automated analysis of large relevant datasets will allow us to do better science, and learn what the true latent dimensions of those behavioral spaces are. And we can hope for convenient, inexpensive, and psychometrically reliable ways to estimate the efficacy of treatments.⠀

I'll present some suggestive preliminary results, and discuss future research opportunities as well as the existing barriers to progress.



  1. D.O. said,

    June 9, 2020 @ 11:20 am



  2. stephen reeves said,

    June 11, 2020 @ 3:34 pm

    what language is the abstract written in ?

  3. Andrew Usher said,

    June 11, 2020 @ 5:58 pm

    Well, it's quoted here in English! It used to be common to require an abstract (or equivalent) in the host or primary language, but I think that's disappearing, at least when the presentation language is English as it almost always is today.

    After several days there is still no explanation of the first comment – a joke I didn't get? Or political commentary of the current situation?

    k_over_hbarc at yahoo.com

    [(myl) The talk will be in English, since I unfortunately am not fluent in Portuguese.

    The first comment was a bad joke, intended (I guess) to question whether taking a day off from STEM research would have any meaningful effect on systemic racism.

    My own opinion, FWIW, is that the intended effect is on the researchers, not the racists. And the impetus to postpone the talk from Thursday to today came from me.]

RSS feed for comments on this post