Mycroft and SNIPS: open source voice assistants

Any excuse to have Sherlock on the blog is good, I say. This time I want to record the fact that there is an open source voice assistant, called Mycroft, code available from GitHub, originating from Kansas City, MO, they say. Mycroft, like Alexa and Bixby, has skills contributed by the community of users. I wanted to buy Mycroft Mark 2, but this seems to be out of stock right now.

The other open source voice assistant is called snips. They have a different storyline in mind and Jarvis is the module that creates a voice assistant for free, in different languages. Then one can deploy the assistant to a Raspberry Pi, an Android or a Linux device. This will run completely on-device, keeping data safe and private! 
The Snips Platform is a software solution powering Private-by-Design voice assistants. Businesses or individuals, anyone can set up the Snips Platform on a single board computer (for example a Raspberry Pi 3, an i.MX8M board, an Android or an iOS device), and install a voice assistant on it.

Alexa has by now apparently 70K skills and I don't know how many `tasks' in Google Home Assistant market place. I wonder if anyone has written a comparison of all these voice frameworks.

Natural Language Inference: over and over again

This post is about collecting the many talks I have given about Natural Language Inference.
The first one is from the beginning of 2017 and has not been written up as a paper, yet. The slides of Universal Dependencies for Inference from Feb 2017 are in SlideShare.

Then the work with Katerina Kalouli and Livy Real, that ended up in several papers, is described in the slide deck Natural Language Inference: logic from humans, from December 2017.

Further,  I talked in Oslo on Natural Language Inference in SICK at the  MAy 2018 workshop on Meaningful Work: Advancing Computational Semantics. There I met Martha Palmer and more collaboration ensued, yay!

Vanity Trip

Nice things in the past? Nah! Building my brand? I wish!

Anyways, this post is about situations where people said nice things about my work.

So, I am very proud of my Wikipediapage,  
https://en.wikipedia.org/wiki/Valeria_de_Paiva. A `friend' suggested that, if I had created my own page, at least I had the grace of not getting caught. With friends like this, who needs enemies, right?

When I was still at Xerox PARC, the MAA did this piece https://www.maa.org/careers/career-profiles/academia-teaching/valeria-de-paiva. After I left PARC, I was invited to come back and give a PARC Forum, something I was never invited to do during the nine years I spent there. I think the talk and the poster (reduced image below) turned out quite well. The video was on the PARC website, at https://www.parc.com/parc-forum/adventures-in-searchland/, but  it's now gone. After all, this was nine years ago. (I think I still have the DVD of the talk, I should try to convert it to digital. update: I did, the talk is now at youtube.)

After  many years, when I was at Nuance, AMS's Math Awareness Month did this interview with me http://www.mathaware.org/mam/2015/highlighted/MAM%202015%20profile_dePaiva.pdf (this seems to have disappeared from the live web, wayback machine to the rescue) and I was delighted.  But the most amazing was to discover, when searching the Web for something else,  this pretty cartoon done by the guys at Karisma.org, from Colombia, within the blog post https://karisma.org.co/que-pasaria-sin-el-aporte-de-las-mujeres-a-la-ciencia-en-el-mundo/.

Sadly the profile that the Samsung comms did about me was only internal and I don't know if I have a copy somewhere. I will add it here if I find it. But recently there was also this  report on this (self-referential) blog which was very cool!

The old poster from MAM (Mathematical Awareness Month) is below, thanks to the Wisconsin Dept of Public Instruction.

 

Old Stories

This amazing picture taken, I presume, at Pico da Neblina, Brazil reminds me very much of Isabel Allende's young adult novel City of the Beasts.  I liked it very much when I first read it. Rechecking it in Wikipedia just now, I guess I  am really not very sophisticated in my love of books.

Anyways, the point of this post is to remember old stories of a very different kind. This deck contains the slides of my first talk at Nuance, in October 2012.

To show, once again, that I really need to be better at organizing my work, I talked about this deck  in this blog post, in this one and in this post.

Old (2017) BACAT slides

I'm pretty useless at keeping track of what I have and have not done and when. So here are the slides from when I talked in BACAT in Sept 2017 about Temporal Logic, "Doing Time, Categorically".

This was a paper with my collaborator Harley Eades III for a special issue of the IfColog Journal in honour of Grigori Mints. I feel that I need to improve on this paper and I also need to carry on with the project of constructive modal logics, but not now, as other requests on my time are taking precedence.

Santa Clara in February

Yesterday I talked at BACAT (Bay Area Categories And Types) and it was a lot of fun. When I searched for my old slides  I thought that I hadn't spoken at BACAT for a long while, since 2014. But this was only because I cannot find anything on my computer. In reality, I had talked in Sept 2017 about temporal logic. Still, this was a long time ago and the old building where Computer Science had classes has been demolished.

But the campus is now looking lovely and I wish I had taken pictures.

The slides for the talk are here.  I liked my title "Going Without: a modality and its role" because the ambiguity works on my favour, for once. The slides are a bit rough, as BACAT talks are fun because you can afford to be tongue-in-cheek and outrageous, if you so wish.

Organizing Talks

Organizing talks is an art, and as such, it can be lots of hard work, as well as plenty of fun. But since it happens bit by bit you can only see how hard you've worked with hindsight. I've organized six years of talks at Nuance Sunnyvale Lab, 202 talks, in total, I believe.

Sure, lots of other people helped too, but I think most of the work was actually mine. There were times that I thought it was a waste of time and thought I'd stop doing it. But I really enjoy listening to engaging talks, and I do have plenty of very engaging friends, so I usually went back to organizing it. Most of the talks were academic and about stuff already published. I do not have the abstracts or slides for most of the talks, so I hope none of the presenters will be offended that in the attachment there is simply a spreadsheet with their name and the titles of the talks.