"Natural Language Access to Data: Where Reasoning Makes Sense"

247 views

Published on

Richard Waldinger from SRI International presented this for the Cognitive Systems Institute Speaker Series on April 7, 2016. To hear a replay go to http://cognitive-science.info/community/weekly-update/

Published in: Technology
0 Comments
0 Likes
Statistics
Notes
  • Be the first to comment

  • Be the first to like this

No Downloads
Views
Total views
247
On SlideShare
0
From Embeds
0
Number of Embeds
6
Actions
Shares
0
Downloads
12
Comments
0
Likes
0
Embeds 0
No embeds

No notes for slide

"Natural Language Access to Data: Where Reasoning Makes Sense"

  1. 1. Natural Language Access to Data: Where Reasoning Makes Sense Richard Waldinger Artificial Intelligence Center SRI International Cognitive Science Institute Speaker Series 7 April 2016 1
  2. 2. natural language access to data joint work Cleo Condoravdi, Stanford University Kyle Richardson, Stuttgart University Asuman Suenbuel, SAP Vishal Sikka, SAP (now Infosys) 2
  3. 3. natural language access to data the problem accessing knowledge from structured data sources. via questions in natural language. 3
  4. 4. natural language access to data why is this hard? natural language uncontrolled. we want answers, not websites. answers deduced or computed. multiple databases. sequence of ongoing queries. 4
  5. 5. natural language access to data what makes it easier? we restrict ourselves to a well-understood subject domain. business enterprise we use already known databases. access to SAP’s HANA database. “Quest” 5
  6. 6. waldinger natural language access to datawaldinger natural language access to data sample query sequence Show a company with a long-term debt within the last two years. The debt is more than 5 million Euros. It must be Swiss. 6
  7. 7. waldinger natural language access to datawaldinger natural language access to data why does this require reasoning? query may be logically complex. to resolve ambiguities in the query. differences in vocabularies. bridge the inferential leap. compose the answer. 7
  8. 8. waldinger natural language access to datawaldinger natural language access to data approach (nl+deduction) semantic parsing ⇒ semantic representation transform ⇒ logical form proof ⇒ answers proof conducted in an axiomatic theory theory contains links to databases. 8
  9. 9. waldinger natural language access to datawaldinger natural language access to data implementation of Quest natural language processing by SAPL (Cascade Parser) reasoning by SRI’s SNARK. data from SAP’s HANA, Currency Conversion, Nationality Tables, etc. 9
  10. 10. waldinger question answering/ deductionwaldinger question answering/ deduction theorem prover (SNARK) resolution (general reasoning). paramodulation, rewriting (equality). sorted unification. answer extraction. procedural attachment. spatial and temporal reasoning. 10
  11. 11. waldinger natural language access to datawaldinger natural language access to data axiomatic subject domain theory defines concepts in queries. expresses capabilities of the databases. provides background knowledge to relate them. sort (type) structure axioms 11
  12. 12. waldinger question answering/ deductionwaldinger question answering/ deduction sort structure entity agent company time interval debt number money size 12
  13. 13. waldinger question answering/ deductionwaldinger question answering/ deduction sorts of relations company-has-debt(<company>, <debt>) company-has-size(<company>, <size>) within(<time interval>, <time interval>) swiss(<agent>) 13
  14. 14. waldinger natural language access to datawaldinger natural language access to data parsing based on PARC natural language technology (XLE + Bridge) new parser (SAPL) written for Quest. parser knows sort structure and sorts of relations. 14
  15. 15. waldinger question answering/ deductionwaldinger question answering/ deduction semantic parsing query: Show a company with a high debt within the last two years. semantic representation (partial): (quant exists company7 sort company) (quant exists debt3 sort debt) (scopes-over company7 debt3) (in nscope debt3 (company-has-debt company7 debt3)) 15
  16. 16. waldinger question answering/ deductionwaldinger question answering/ deduction logical form (exists ((company7 sort company) (debt3 sort debt) (time-interval5 sort time-interval)) (and (company-has-debt company7 debt3) (within debt3 time-interval5) (time-measure time-interval5 2 year) (last time-interval5)) 16
  17. 17. waldinger question answering/ deductionwaldinger question answering/ deduction axiom: definition of high debt high(debt-record(?company, ?money,…)) ⇔ ?money > dollars(1000000) i.e., a debt is high if its money amount is greater than 1 million dollars. 17
  18. 18. waldinger question answering/ deductionwaldinger question answering/ deduction axiom: company has debt company-has-debt(?company, ?debt) ⇔ (exists (?location, ?size, ?dso, ….) company-record(?company, ?debt, ?location, ?size, ?dso, ….) & positive(?debt) procedural attachment 18
  19. 19. waldinger nl access to datawaldinger nl access to data sample data name money location date SL Foods Inc. $105263551.70 CH 2007 Sept. 1 19 name: SL Foods Inc. amount of debt: $105,263,551.70. date debt incurred: Sept 1, 2007. nationality: CH (Switzerland) ...
  20. 20. waldinger question answering/ deductionwaldinger question answering/ deduction the answer(s) the debt of sl food inc. is high, the debt of sl food inc. is within the interval from 9/1/2006 to 9/1/2008, the duration of the interval from 9/1/2006 to 9/1/2008 is 2 years, the interval from 9/1/2006 to 9/1/2008 is last. 20
  21. 21. waldinger question answering/ deductionwaldinger question answering/ deduction reasoning resolves ambiguity. Show me a client with a high debt. It was within the last 2 years. (“It” must be the debt). It should be Swiss. (“It” must be the client) 21
  22. 22. waldinger question answering/ deductionwaldinger question answering/ deduction crowd-sourced axiomatic theories we currently translate english questions into logical form. we could also translate declarative sentences into logical form. develop axiomatic theory from text. domain experts need not know logic. 22
  23. 23. waldinger question answering/ deductionwaldinger question answering/ deduction other future work other domains. spoken input. efficiency. changing data bases. 23
  24. 24. waldinger question answering/ deductionwaldinger question answering/ deduction reference Natural Language Access to Data: It Takes Common Sense AAAI Symposium: Logical Formalizations of Common Sense Reasoning 24

×