Benjamin Grosof and I will be presenting the following review of recent work at Vulcan towards Digital Aristotle as part of Project Halo at SemTechBiz in San Francisco the first week of June.
Acquiring deep knowledge from text
We show how users can rapidly specify large bodies of deep logical knowledge starting from practically unconstrained natural language text.
English sentences are semi-automatically interpreted into predicate calculus formulas, and logic programs in SILK, an expressive knowledge representation (KR) and reasoning system which tolerates practically inevitable logical inconsistencies arising in large knowledge bases acquired from and maintained by distributed users possessing varying linguistic and semantic skill sets who collaboratively disambiguate grammar, logical quantification and scope, co-references, and word senses.
The resulting logic is generated as Rulelog, a draft standard under W3C Rule Interchange Format’s Framework for Logical Dialects, and relies on SILK’s support for FOL-like formulas, polynomial-time inference, and exceptions to answer questions such as those found in advanced placement exams.
We present a case study in understanding cell biology based on a first-year college level textbook.
Working as part of Vulcan’s Project Halo, Automata is applying a natural language understanding system that translates carefully formulated sentences into formal logic so as to answer questions that typically require deeper knowledge and inference than demonstrated by Watson.
The objective over the next three quarters is to acquire enough knowledge from the 9th edition of Campbell’s Biology textbook to demonstrate three things.
- First, that the resulting system answers, for example, biology advanced placement (AP) exam questions more competently than existing systems (e.g., Aura or Inquire).
- Second, that knowledge from certain parts of the textbook is effectively translated from English into formal knowledge with sufficient breadth and depth of coverage and semantics.
- Third, that the knowledge acquisition process proves efficacious and accessible to less than highly skilled knowledge engineers so as to accelerate knowledge acquisition beyond 2012.
Included in the second of these is a substantial ontology of background knowledge expected of students in order to comprehend the selected parts of the textbook using a combination of OWL, logic, and English sentences from sources other than the textbook.
Automata is hiring logicians, linguists, and biologists to work as consultants, contracts, or employees for:
- Interactive tree-banking and word-sense disambiguation of several thousand sentences.
- Extending its lexical ontology and a broad-coverage grammar of English with additional vocabulary and deeper semantics, especially concerning cellular biology and related scientific knowledge including chemistry, physics, and math.
- Maturing its upper and middle ontology of domain independent knowledge using OWL in combination with various other technologies, including description logic, first-order logic, high-order logic, modal logic, and defeasible logic.
- Enhancing its platform for text-driven knowledge engineering towards a collaborative wiki-like architecture for self-aware content in scientific education and biomedical applications.
Terms of engagement are flexible; ranging from small units of work to full-time employment. We are based in Pittsburgh, Pennsylvania and Vulcan is headquartered in Seattle, Washington, but the team is distributed across the country and overseas.
Please contact Paul Haley by e-mail to his first name at this domain.
; Project Halo: http://www.projecthalo.com/
Video introduction/overview :http://videolectures.net/aaai2011_gunning_halobook/
 Aura: http://www.ai.sri.com/project/aura
 Inquire: http://www.franz.com/success/customer_apps/artificial_intelligence/aura.lhtml
 tree-banking and WSD: http://www.omg.org/spec/SBVR and http://en.wikipedia.org/wiki/Word-sense_disambiguation
 e.g., SILK (http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.174.1796 ) and SBVR (http://www.omg.org/spec/SBVR)
Being a fan of increased intelligence on the web, including Bing’s use of Powerset and True Knowledge, I enjoyed cnet’s report, “Google search gets answer highlights and events.”
Google now shows the following “The Empire State Building rises to 1250 ft (381 m) at the 102nd floor” in response to the classic semantic web test question.
Also, Google leverages more of the content of text or structure of linked data in its Rich Snippet answers:
As search engines increase their understanding of concepts and how to extract them from content or linked data and present them as Google does here or above in a sentence, the web will begin to feel a lot smarter.
As these simple enhancements indicate, the intelligent web is taking off and that feeling of intelligence will come sooner than expected. Of course, there is a long way to go. For more on that, I here there is an upcoming issue of AI Magazine that will survey the state of the art in question answering, including coverage of Vulcan’s Project Halo and IBM’s Jeopardy effort, among others. Also, if you are interested in what bright minds are looking forward to in this regard, see Nova Spivak’s recent blogging and his post on “will the web become conscious?”
Work on acquiring knowledge about science has estimated the cost of encoding knowledge in question answering or problem solving systems at $10,000 per page of relevant textbooks. Regrettably, such estimates are also consistent with the commercial experience of many business rules adopters. The cost of capturing and automating hundreds or thousands of business rules is typically several hundred dollars per rule. The labor costs alone for a implementing several hundred rules too often exceed $100,000.
The fact that most rule adopters face costs exceeding $200 per rule is even more discouraging when this cost does not include the cost of eliciting or harvesting functional requirements or policies but is just the cost of translating such content into the more technical expressions understood by business rules management systems (BRMS) or business rule engines (BRE).
I recommend against adopting any business rule approach that cannot limit the cost of automating elicited or harvested content to less than $100 per rule given a few hundred rules. In fact, Automata provides fixed price services consistent with the following graph using an approach similar to the one I developed at Haley Systems.
Continue reading “The $50 Business Rule”