This is very similar to my own view of the topic, except that I have very specific ideas as to how placement and payload are arranged in the sentence or language fragment based on the (possibly incomplete) grammatical relationships implied within it, and how those grammatical relationships map to semantic relationships. The implied relationships between elements of a sentence (typically represented through prepositions and/or SVO relationships) serve as relational search constraints between entity patterns (typically represented as noun or verb phrases). The payload is the assertion of the most important grammatical element, which is the verbally stressed element, if there is one, or the head verb phrase, if no verbal stressing was applied. In the event of an incomplete sentence fragment, missing entities that are logically necessary are supplied based on context. For example, if someone leaves off the subject of a sentence, the most compatible entity matched in the previous discourse (or physical setting, if appropriate) will be selected, which will often be the speaker. Substitution of missing phrases works much like anaphora resolution, in other words.
On Wed, Mar 27, 2013 at 11:27 PM, Steve Richfield <[email protected] > wrote: > *Jim, et al,* > > > *I'm starting a new thread with this...* > > ** > > It is my theory that computerized speech and text understanding has eluded > developers for the past ~40 years, because of a lack of a fundamental > understanding of the task, which turns out to be very similar to patent > classification. > > > When classifying a patent, successive layers of sub-classification are > established, until only unique details distinguish one patent from another > in the bottom-level subclass. When reviewing the sub-classifications that a > particular patent is filed within, combined with the patent’s title, what > the patent is all about usually becomes apparent to anyone skilled in the > art. > > > However, when a patent is filed into a different patent filing system, > e.g. filed in a different country where the sub-classifications may be > quite different, it may be possible that the claims overlap the claims of > other patents, and/or unclaimed disclosure would be patentable in a > different country. > > > Similarly, when you speak or write, in your own mind, most of your words > are there to place a particular “payload” of information into its proper > context, much as patent disclosures place claims into the state of an art. > However, your listeners or readers may have a very different context in > which to file your words. They must pick and choose from your words in an > effort to place some of your words into their own context. What they end up > placing may not even be the “payload” you intended, but may be words you > only meant for placement. Where no placement seems possible, they might > simply ignore your words and file *you* as being ignorant or deranged. > > > Many teachers have recorded a classroom presentation and transcribed the > recording, only to be quite surprised at what they actually said, which can > sometimes be the opposite of what they meant to say. Somehow the class > understood what they meant to say, even though their statement was quite > flawed. When you look at these situations, the placement words were > adequate, though imperfect, but the payload was okay. Indeed, where another > person’s world model is nearly identical to yours, very few placement words > are needed, and so these words are often omitted in casual speech. > > > These omitted words fracture the structure of around half of all sentences > “in the wild”, rendering computerized parsing impossible. Major projects, > like the Russian Academy of Science’s Russian Translator project, have > wrestled with this challenge for more than a decade, with each new approach > producing a better result. The results are still far short of human > understanding due to the lack of a human-level domain context to guide the > identification and replacement of omitted words. > > > As people speak or write to a computer, the computer must necessarily have > a *very* different point of view to even be useful. The computer must be > able to address issues that you can not successfully address yourself, so > its knowledge must necessarily exceed your own in its subject domain. This > leads to some curious conclusions: > > 1. Some of your placement words will probably be interpreted as > “statements of ignorance” by the computer and so be processed as valuable > payload to teach you. > > 2. Some of your placement words will probably refer to things outside of > the computer’s domain, and so must be ignored, other than being recognized > as non-understandable restrictions on the payload, that may itself be > impossible to isolate. > > 3. Some of your intended “payload” words must serve as placement, > especially for statements of ignorance. > > My invention seeks to intercept words written to other people who > presumably have substantial common domain knowledge. Further, the computer > seeks to compose human-appearing responses, despite its necessarily > different point of view and lack of original domain knowledge. While this > is simply not possible for the vast majority of writings, the computer can > simply ignore everything that it is unable to usefully respond to. > > > If you speak a foreign language, especially if you don’t speak it well, > you will immediately recognize this situation as being all too common when > listening to others with greater language skills than your own speaking > among themselves. The best you can do is to quietly listen until some point > in the conversation when you understand enough of what they are saying, and > you have something useful to add to the conversation. > > > Note the similarity to the advertising within the present Google Mail, > where they select advertisements based upon the content of email that is > being displayed. Had Google performed a deeper analysis they could probably > eliminate ~99% of the ads as not relating to users’ needs and greatly > improve the users’ experience, and customize the remaining 1% of the ads to > precisely target the users. > > > That is very much the goal with my invention, where the computer knows > about certain products and solutions to common problems, etc., and scans > the vastness of the Internet to find people whose words have stated or > implied a need for things in the computer’s knowledge base, and have done > so in terms that the computer can “understand”. > > Steve > =============== > On Wed, Mar 27, 2013 at 10:56 AM, Jim Bromer <[email protected]> wrote: > >> Steve, >> No I haven't. Where can I find it? >> Jim >> >> On Wed, Mar 27, 2013 at 10:26 AM, Steve Richfield < >> [email protected]> wrote: >> >>> Jim, >>> >>> Have you looked at my placement/payload view of grammar and semantics? >>> >>> Note that the job of people who edit is to improve grammar and >>> simplicity of expression. The mere presence of such people is an indictment >>> of well-structured grammar. >>> >>> Steve >>> ================== >>> On Wed, Mar 27, 2013 at 7:16 AM, Jim Bromer <[email protected]> wrote: >>> >>>> I like Hausser’s system but it does not solve the kinds of problems >>>> that I need to solve. His left associative system with the pointer or >>>> address to other parts of associated speech certainly seem more sensible >>>> then the grammars that use a method of direct substitution to determine >>>> whether the formation of a sentence is grammatical. But I am more >>>> interested in the meaning of sentences and I believe that there is too much >>>> that the theories of elementary formal grammar have not solved. I >>>> haven’t finished the paper that Hausser sent but I will get back to it in a >>>> few weeks. >>>> >>>> >>>> >>>> I believe that the initial interpretation of sentences partly relies on >>>> the meaning and roles of words that can be learned but which are not >>>> necessarily found from within a strict partitioning of the constituents and >>>> elements and fundamental systems of the grammar. So, just as >>>> Hausser’s grammar seems a little more sensible than the strictly >>>> substitutional generative grammars, I believe that we need to find a way to >>>> combine more from semantics into the initial stages of recognition. These >>>> rules should be largely associative and could be expressed as >>>> substitutions, but they may not be found from a conventional analyses of >>>> how these fundamental systems may be generated. So the most >>>> unconstrained system of formal generative grammar might be needed to >>>> express the range of human language but once the grammatical sentences of >>>> the language were found it might turn out that they can be expressed by >>>> simpler systems. The conclusion of my thought on this would be to say >>>> that we need a greater freedom to discover the relationships between words >>>> and phrases to discover how words are used to govern the discovery of the >>>> meaning of the expressions. Words and phrases are used to convey >>>> ideas but they also convey the instructions on how to encode and decode the >>>> words and phrases of the expressions used. Formal generative grammar >>>> was an attempt to figure out how this is done but I think the study of the >>>> subject got a little sidetracked onto the problems of defining >>>> a computational system of what is ‘grammatical’ rather than what is that is >>>> to be understood. >>>> >>>> >>>> >>>> But Hausser has given us a little more freedom to use in our attempts >>>> to figure this problem out. >>>> >>>> Jim >>>> >>>> >>>> On Sun, Mar 24, 2013 at 5:00 PM, Piaget Modeler < >>>> [email protected]> wrote: >>>> >>>>> >>>>> >>>>> ------------------------------ >>>>> Date: Sun, 24 Mar 2013 10:43:26 +0100 >>>>> Subject: Re: Parsing Natural Language >>>>> From: Roland Hausser >>>>> To: [email protected] >>>>> >>>>> >>>>> Hello Mike, >>>>> >>>>> Thank you for your email and the comments by >>>>> Jim Bromer and Steve Richfield. They touch >>>>> on some very general issues which are difficult >>>>> to address specifically. Therefore I attach a >>>>> recent paper which appeared in >>>>> >>>>> Semantics in Data and Knowledge Bases: 5th International >>>>> Workshop SDKB 2011, Zürich, Switzerland, July 3, 2011, >>>>> Revised Selected Papers (LNCS 7693 >>>>> Applications, incl. Internet/Web, and HCI) [Paperback] >>>>> Klaus-Dieter Schewe (Editor), Bernhard Thalheim (Editor) >>>>> ISBN-10: 3642360076 >>>>> ISBN-13: 978-3642360077 >>>>> >>>>> The editors asked for an introduction to DBS, giving >>>>> me space. >>>>> >>>>> Please pass the .pdf on to those in your group who are >>>>> interested. Looking forward for to further reactions, >>>>> >>>>> Cheers, >>>>> >>>>> Roland >>>>> >>>>> *AGI* | Archives <https://www.listbox.com/member/archive/303/=now> >>>> <https://www.listbox.com/member/archive/rss/303/10443978-6f4c28ac> | >>>> Modify <https://www.listbox.com/member/?&;> Your Subscription >>>> <http://www.listbox.com> >>>> >>> >>> >>> >>> -- >>> Full employment can be had with the stoke of a pen. Simply institute a >>> six hour workday. That will easily create enough new jobs to bring back >>> full employment. >>> >>> *AGI* | Archives <https://www.listbox.com/member/archive/303/=now> >>> <https://www.listbox.com/member/archive/rss/303/10561250-470149cf> | >>> Modify <https://www.listbox.com/member/?&;> Your Subscription >>> <http://www.listbox.com> >>> >> >> *AGI* | Archives <https://www.listbox.com/member/archive/303/=now> >> <https://www.listbox.com/member/archive/rss/303/10443978-6f4c28ac> | >> Modify <https://www.listbox.com/member/?&;> Your Subscription >> <http://www.listbox.com> >> > > > > -- > Full employment can be had with the stoke of a pen. Simply institute a six > hour workday. That will easily create enough new jobs to bring back full > employment. > > *AGI* | Archives <https://www.listbox.com/member/archive/303/=now> > <https://www.listbox.com/member/archive/rss/303/23050605-2da819ff> | > Modify<https://www.listbox.com/member/?&;>Your Subscription > <http://www.listbox.com> > ------------------------------------------- AGI Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/21088071-f452e424 Modify Your Subscription: https://www.listbox.com/member/?member_id=21088071&id_secret=21088071-58d57657 Powered by Listbox: http://www.listbox.com
