Natural Language Access to Data
via
Deduction
Richard Waldinger
Artificial Intelligence Center
SRI International
Cognitive...
natural language access to data
joint work
Cleo Condoravdi, Stanford University
Kyle Richardson, Stuttgart
University
Asum...
natural language access to data
the problem
accessing knowledge
from structured data sources.
via questions in natural
lan...
natural language access to data
why is this hard?
natural language uncontrolled.
we want answers, not websites.
answers de...
natural language access to data
what makes it easier?
we restrict ourselves to a well-understood
subject domain.
business ...
waldinger natural language access to datawaldinger natural language access to data
sample query sequence
Show a company wi...
waldinger natural language access to datawaldinger natural language access to data
why does this require reasoning?
query ...
waldinger natural language access to datawaldinger natural language access to data
approach (nl+deduction)
semantic parsin...
waldinger natural language access to datawaldinger natural language access to data
implementation of Quest
natural languag...
waldinger question answering/ deductionwaldinger question answering/ deduction
theorem prover (SNARK)
resolution (general ...
waldinger natural language access to datawaldinger natural language access to data
axiomatic subject domain theory
defines...
waldinger question answering/ deductionwaldinger question answering/ deduction
sort structure
entity
agent
company
time in...
waldinger question answering/ deductionwaldinger question answering/ deduction
sorts of relations
company-has-debt(<compan...
waldinger natural language access to datawaldinger natural language access to data
parsing
based on PARC natural language
...
waldinger question answering/ deductionwaldinger question answering/ deduction
semantic parsing
query: Show a company with...
waldinger question answering/ deductionwaldinger question answering/ deduction
logical form
(exists ((company7 sort compan...
waldinger question answering/ deductionwaldinger question answering/ deduction
procedural attachment
company-has-debt(?com...
waldinger nl access to datawaldinger nl access to data
sample data
name money location date
SL Foods Inc. $105263551.70 CH...
waldinger question answering/ deductionwaldinger question answering/ deduction
the answer(s)
the debt of sl food inc. is h...
waldinger question answering/ deductionwaldinger question answering/ deduction
reasoning resolves ambiguity.
Show me a cli...
waldinger question answering/ deductionwaldinger question answering/ deduction
future work
we currently translate english
...
waldinger question answering/ deductionwaldinger question answering/ deduction
reference
Natural Language Access to Data:
...
of 22

Natural Language Access to Data via Deduction

Richard Waldinger, principal scientist in SRI's Artificial Intelligence Center, made this presentation at the Cognitive Systems Institute Speaker Series on February 18, 2016.
Published on: Mar 3, 2016
Published in: Technology      
Source: www.slideshare.net


Transcripts - Natural Language Access to Data via Deduction

  • 1. Natural Language Access to Data via Deduction Richard Waldinger Artificial Intelligence Center SRI International Cognitive Science Institute Speaker Series 18 February 2016 1
  • 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. natural language access to data the problem accessing knowledge from structured data sources. via questions in natural language. 3
  • 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. 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. 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. 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. 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. 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. 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. 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. waldinger question answering/ deductionwaldinger question answering/ deduction sort structure entity agent company time interval debt number money size 12
  • 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. 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. 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. 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. waldinger question answering/ deductionwaldinger question answering/ deduction procedural attachment company-has-debt(?company, ?debt) ⇔ (exists (?location, ?size, ?dso, ….) company-record(?company, ?debt, ?location, ?size, ?dso, ….) & positive(?debt) 17
  • 18. waldinger nl access to datawaldinger nl access to data sample data name money location date SL Foods Inc. $105263551.70 CH 2007 Sept. 1 18 name: SL Foods Inc. amount of debt: $105,263,551.70. date debt incurred: Sept 1, 2007. nationality: CH (Switzerland) ...
  • 19. 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. 19
  • 20. 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) 20
  • 21. waldinger question answering/ deductionwaldinger question answering/ deduction future work 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. 21
  • 22. 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 22

Related Documents