ddahl [~ddahl@team.cloak] entered the room.

ddahl

many mobile assistants are based on natural language

siri, cortana, google now

why concede this space to proprietary solutions?

what about enterprise specific

doesn't scale

ddahl

bert: thing on the web that's not a browser

ddahl

scribe: doesn't need speech interaction but maybe gestures
... natural language is too chatty for typing

debbie: there could be much more dialog-like

ddahl

bert: would like to control the output

ddahl

debbie: Siri often gives you just Wikipedia
... maybe an open source platform that you could customize, e.g. load the sports module
... good for accessibility
... skip advertising
... would like to be able to ask for links on the page
... could index conversations by location, time, topic
... should be able to encode data visualization
... in a way that you like or different ways

ddahl

bert: saw something that looked at the links and several levels of links past that

ddahl

debbie: EMMA 2.0 can support multimodal fission to allocate levels of concreteness to an output

ddahl

bert: regularize navigation in a web page, e.g. a standard table of contents

ddahl

scribe: could generate table of contents from a web page

debbie: browers haven't become user-friendly

ddahl

bert: often uses text browsers or curl to just get information, or just uses atom or rss feed

<ddahl> debbie: bert's requirements -- doesn't need speech, more interested in desktop, not really interested in natural language

<ddahl> ...could be interested in a history of interactions and then bringing them back

<ddahl> bert: Opera allows user style sheets

<ddahl> ...but Opera doesn't have per-site style sheets

<ddahl> ...possible with Mozilla

<ddahl> ...but can't reorder

<ddahl> ...would also like to do this with non-web info like mail

<ddahl> debbie: could also go to REST API's, for example Best Buy

<ddahl> bert: mobile sites are sometimes better

<ddahl> ...also easier to scrape

<ddahl> debbie: this isn't what I expected, but interesting

<ddahl> ...more interested in accessing semantics of page

<ddahl> debbie: would be nice to also integrate best practices from other sites with information

This is scribe.perl Revision: 1.140  of Date: 2014-11-06 18:16:30  
Check for newer version at http://dev.w3.org/cvsweb/~checkout~/2002/scribe/

Guessing input format: RRSAgent_Text_Format (score 1.00)

No ScribeNick specified.  Guessing ScribeNick: Bert1
Inferring Scribes: Bert1

WARNING: No "Topic:" lines found.

Present: debbie bert

WARNING: Fewer than 3 people found for Present list!

Got date from IRC log name: 28 Oct 2015
Guessing minutes URL: http://www.w3.org/2015/10/28-pa-minutes.html
People with action items: 

WARNING: No "Topic: ..." lines found!  
Resulting HTML may have an empty (invalid) <ol>...</ol>.

Explanation: "Topic: ..." lines are used to indicate the start of 
new discussion topics or agenda items, such as:
<dbooth> Topic: Review of Amy's report