W3C home > Mailing lists > Public > public-cogai@w3.org > July 2020

Re: Simulated natural language dialogue

From: Paola Di Maio <paola.dimaio@gmail.com>
Date: Sun, 19 Jul 2020 15:46:21 +0800
Message-ID: <CAMXe=SpH1c4pv+THVnqWCecxEsRKhfURESmP-FCx=F9i_2bXXw@mail.gmail.com>
To: Dave Raggett <dsr@w3.org>
Cc: public-cogai@w3.org
I dont think we need to have intelligent conversations to order food
(intelligence not required for this task, why bother)
its a simple interactive routine will suffice, as long as it does
everything that is requrred

and also: add some subroutine/subtask
after ordering, A- customer should be able to specify preferences, such as
extra chees, no onions, medium vs rare etc

PDM

On Sat, Jul 18, 2020 at 10:56 AM Paola Di Maio <paola.dimaio@gmail.com>
wrote:

> Let me add
>
> looks like you are trying to reproduce an intelligent conversation between
> two humans
> (nice job!) but based on my experience, there are many things that can go
> wrong with that approach
> in a real-world situation that the system would not be  able to handle
> (unless it's a very expensive system that can handle any situation)
>
> while in my example I try to complete a set of tasks with the least amount
> of effort and minimum risk of going wrong
> so I think I understand why you are doing it that way, but I think I would
> model the exchange differently
> to reduce uncertainty hence effort required to get the task accomplished
>
> P
>
>
> On Sat, Jul 18, 2020 at 10:51 AM Paola Di Maio <paola.dimaio@gmail.com>
> wrote:
>
>> So - from the KR point of view, I would simply use very informative lists
>> of options for each task
>> T= task
>> A= agent
>>
>> T1 - GREETINGS (where the variables are a time of the day and is only
>> sir/madam etc)
>> A1/A2 (Agent)
>>
>> T2- A1 offer of service (list of options)
>> T2.1 choose table,
>> T2.2. order food ,
>> T2.3 order drink
>> T2.4 anything else (information about toilet, phone, other info)
>>
>>
>> T3 -  A2 requests more information (thats the tricky bit - A2 the
>> customer would want to know
>> if the mushrooms are fresh or frozen, if the fish comes from sustainable
>> sources, what is the percentage of blueberry in the jam etc)
>>
>> Ideally, the KR for T3 is carried in such a way that all the possible
>> information about the food and drink choice is available to the
>> the customer before they order
>> so the menu would list the foods and drinks and also have a
>> page/narrative associated with them
>> that would list exclusions (dont eat this if you are allergic to.....)
>> and calorie count etc etc
>>
>> If you think this would be useful I can write it up more clearly
>>
>> PDM
>>
>>
>> On Sat, Jul 18, 2020 at 10:31 AM Paola Di Maio <paola.dimaio@gmail.com>
>> wrote:
>>
>>> Thank you Dave
>>> Neat stuff!
>>>
>>> good example of how a simple human interaction needs a lot of thinking
>>> and planning to be reproduced-
>>> I ll be interested in the implementation, is there going to be a demo?
>>>
>>> My approach is a bit different, in the sense that I would never attempt
>>> to reproduce a human level conversation
>>> (which you do well in your example) and I would expect that a
>>> conversational agent would be implemented in a highly digitized environment
>>> where there is not need to tell the customer that the table x is not
>>> available and that the dish y is not available
>>> because in a digital environment this information would be updated in
>>> the system
>>>
>>> I ll be more narrow to get (probably) the same result (the table and the
>>> food ordered) with less thinking
>>> for example, I d go more about
>>>
>>> waiter - welcome, what can I do for you?  //maybe provide a list of
>>> options, like order now, reserve for later or  after order service follow
>>> up on a an earlier order such as enquire about lost and found items or a
>>> credit card charge etc)
>>> customer - order dinner/meal, please
>>> waiter- here or takeaway?
>>> customer - here
>>> waiter - please choose your table from those available (from a table
>>> plan /map)
>>> /I would assume the customer figures out that there is no available
>>> table near the window if it is not on the available seats plan which is
>>> updated every time a customer arrives/leaves//
>>> waiter-  here is the menu
>>> //I would assume if an item is not available /off it would not be on the
>>> menu!! which is digitally updated every minute//
>>> etc etc
>>>
>>> I would also want a button that says çall me the human please always
>>> flashing
>>>
>>> So the bottom line of my comment here is that we develop automated
>>> agents thinking of a nonautomated deployment environment
>>> I think thats a bit of a general flaw
>>>
>>> PDM
>>>
>>>
>>>
>>> On Fri, Jul 17, 2020 at 9:20 PM Dave Raggett <dsr@w3.org> wrote:
>>>
>>>> Natural language will be key to future human-machine collaboration, as
>>>> well as to being able to teach everyday skills to cognitive agents. There
>>>> are many potential market opportunities, and many challenges to overcome.
>>>>
>>>> I previously developed a simple demo for natural language parsing based
>>>> around the Towers of Hanoi game. This demo uses very simple language, and
>>>> allows you to type or speak the command to move discs between pegs. The
>>>> demo uses a shift-reduce parser with the parse tree represented in chunks.
>>>>
>>>> https://www.w3.org/Data/demos/chunks/nlp/toh/
>>>>
>>>> I am now working on a more ambitious demo featuring a dialogue between
>>>> a waiter and a customer dining at a restaurant. The idea is to have a
>>>> single web page emulate the waiter and customer as separate cognitive
>>>> agents, and for each agent to apply natural language generation and
>>>> understanding as they each take turns to speak and listen to each other.
>>>> The text they speak will be shown with chat bubbles in a manner familiar
>>>> from smart phone chat services. The demo scenario was chosen as the
>>>> language usage, the semantics and pragmatics are well understood and
>>>> limited in scope.
>>>>
>>>> The aim is to support word by word incremental concurrent processing of
>>>> syntax and semantics without backtracking. This selects the most
>>>> appropriate meaning given the preceding words, the dialogue history and
>>>> other knowledge through the application of rules and graph algorithms,
>>>> including spreading activation. This process works in reverse for natural
>>>> language generation.
>>>>
>>>> My starting point has been to define a dinner plan as a sequence of
>>>> stages (greetings, find table, read menu, place order, …), where each stage
>>>> links to the following stage. I’ve represented the utterances as a sequence
>>>> of chunks, where each utterance links to the previous utterance, and to the
>>>> associated stage in the plan. This has involved a commitment to a small set
>>>> of speech acts, e.g. greeting, farewell, assertion, question, and answer,
>>>> along with positive and negative acknowledgements that are associated with
>>>> additional information.
>>>>
>>>> Along the way, I am evolving a means to represent the parse trees for
>>>> utterances as linked chunks, and will next work on the semantics and
>>>> pragmatics for polite discourse.  I also want to explore how to use the
>>>> statistics in natural language understanding (competence) for natural
>>>> language generation (performance). You can follow my progress  on the
>>>> following page:
>>>>
>>>> https://github.com/w3c/cogai/blob/master/demos/nlp/dinner/README.md
>>>>
>>>> Note: you will need to click the bottom of the section on knowledge
>>>> representation to view the chunk representation of the utterances including
>>>> the parse trees.
>>>>
>>>> If anyone would like to help with this work, including offering
>>>> guidance, please get in touch!
>>>>
>>>> Many thanks,
>>>>
>>>> Dave Raggett <dsr@w3.org> http://www.w3.org/People/Raggett
>>>> W3C Data Activity Lead & W3C champion for the Web of things
>>>>
>>>>
>>>>
>>>>
>>>>
Received on Sunday, 19 July 2020 07:47:13 UTC

This archive was generated by hypermail 2.4.0 : Sunday, 19 July 2020 07:47:14 UTC