Download presentation
Presentation is loading. Please wait.
Published byKeenan Lowden Modified over 9 years ago
1
Question Answering with deep reasoning Chitta Baral, Arizona State U. Michael Gelfond, Texas Tech U. Richard Scherl, Monmouth Univ.
2
Text repository Question Domain Knowledge Module N Reasoning Module k Domain Knowledge Module 1 Reasoning Module 1 Processed Text Answer, possibly with explanation
3
Core efforts with support structures Domain Knowledge Modules –Travel Module -- various –Support structure AnsProlog GUI [demo] Hiro AnsProlog Modules [demo] Luis KR Modules (AnsProlog + Prolog + Constraint LP) -- Dallas Knowledge Modeling [slides] Chitta Consistency restoring (CR-Prolog) -- last site visit Probabilistic reasoning (P-log) -- Tampa Further development of action languages Reasoning Modules –Detecting lies [slides] Chitta –Trying your best to achieve something [slides] Jicheng –Prediction, planning, explanation -- Baltimore –Counterfactuals -- ongoing Explanation generation modules –What is an explanation with respect to an answer set [slides] Jicheng
4
Bridge-building efforts – towards an integrated system Logical Form to extracted facts -- Dallas English to Link grammar output to extracted facts [slides] Luis Collaborative Curation [demo] Chitta AQUAINT web site
5
Knowledge Modeling – objects and properties Trip – basic static attributes – name: a string of characters stops: an ordered list of locations % can be represented as a set of pairs % { (0, locn_0), (1, locn_1)..., (n, locn_n) } % note : locations may be repeated in the list % for trips that include multiple visit % to the same location –derived static attributes – origin: location destination: location intermediate_stops: set of locations number_of_planned_stops: integer
6
Objects and properties -- Cont. –basic fluent attributes: position: location union {en_route} %encodes current location last_planned_stop_number: integer participants: set of persons – derived fluent attributes: next_planned_stop: location directly_associated actions: {depart, stop, embark, disembark} directly_associated actions: {embark, disembark} Person – basic static attributes – name: a string of characters position: location Location – basic static attributes – name: a string of characters
7
Actions name: a string of characters parameters: set of property classes executability conditions: fluent formulas conditional effects: list of pairs (phi, f) where phi is a fluent formula, and f is a fluent literal actor: triggers: list of pairs (phi, a) where phi is a fluent formula, and a is an action depart is_an action –name: depart –parameter: {trip} –executability conditions: trip.position \neq enroute, trip.number_of_planned_stops < trip.last_planned_stop_number –conditional effects: { (T, trip.position = en_route) }
8
Actions (cont.) stop is_an action –name: stop –parameter: {trip.location} –executability condition: trip.position = enroute –conditional effects: { (T, trip.position = trip.location) } embark is_an action – name: embark – parameter: {trip, person} – actor: person – executability condition: trip.participant does_not_include person, trip.position = person.position, trip.position \neq en_route – conditional effects: { (T, trip.participant includes person) } disembark is_an action – name: disembark – parameter: {trip, person} – actor: person – executability condition: trip.participant includes person, trip.position \neq en_route – conditional effects: { (T, trip.participant does_not_include person) }
9
Compound actions and constraints go_on is_a compound_action –name: go_on –component actions: {embark, disembark} CONSTRAINTS –% connect various properties. –% for example: The position of a trip and a participant of that trip are always the same.
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.