Transcript slide presentation

A Knowledge-Driven Approach to
Meaning Processing
Peter Clark
Phil Harrison
John Thompson
Boeing Mathematics and Computing Technology
Goal
• Answer questions about text, especially questions
which go beyond explicitly stated facts
“China launched a meteorological satellite into orbit
Wednesday, the first of five weather guardians to be sent
into the skies before 2008.”
• Suggests:
• there a rocket launch
• China owns the satellite
• the satellite is for monitoring weather
• the orbit is around the Earth
• etc.
None of these are explicitly stated in the text
Meaning Processing
Meaning processing  construction of a situation-specific
representation of the scenario described by text.
• May include elements not explicit in the text
• Operational definition:
Degree of “captured meaning”  ability to answer
questions about the scenario being described
Text
Representation
(Assembled from
prior expectations)
Question-Answering
(Inference)
Underlying Philosophy
• Meaning processing is fundamentally a modeling activity:
– matching what is said with our expectations about the
way the world can be
– creating (assembling) a model of the scenario being
described from a library of pre-built, prototypical
scenarios
Text suggests scenarios which may be appropriate
Scenarios suggest ways of interpreting text
• Somewhat of a “Schankian” approach…
Approach
Heavily expectation-based:
• Build knowledge-base of prototypical scenarios
– e.g., “launching a satellite”
• Extract fragments of information from text
– e.g. subject-verb-object tuples
• Find scenario(s) best matching the text
– drives disambiguation and coersion of the text
– scenario provides info unstated in the text
Scenario Representations
• Identify and label the “key participants”
• Encode relationships between them in a KR language
– Use of prototypes
• Using WordNet’s “ontology” (pragmatic decision)
cargo_n1
satellite_n1
vehicle_n1
rocket_n1
cargo_n1
location_n1
launchpad_n1
location_n1
agent_n1
launch-a-satellite_v1
vehicle_n1
step_n1
countdown_n1
entity_n1
agent_n1
agent_n1
fly_v1
before_r1
destination_n1
orbit_n1
Scenario Representation (simplified)
(encoded in the KM language)
(launch-a-satellite_v1 has
(superclasses (launch_v1 transport_v1))
(text-definition ("An event that begins when ….”)))
(every launch-a-satellite_v1 has
(step_n1 ((a countdown_n1 with
(location_n1 ((the location_n1 of Self)))
(event_n1 ((the fly_v1 step_n1 of Self)))
(before_r1 ((the fly_v1 step_n1 of Self))))
(a fly_v1 with
(vehicle_n1 ((the vehicle_n1 of Self))) )))
(vehicle_n1 ((a rocket_n1)))
(cargo_n1 ((a satellite_n1)))
(locaton_n1 ((a launchpad_n1)))
(agent_n1 ((a entity_n1)))))
Representations are Compositional (1)
place_v1
object_n3
entity_n1
step_n1
object_n3
entity_n1
agent_n1
destination_n1
move_v1
cargo_n1
satellite_n1
vehicle_n1
rocket_n1
+
launch-a-satellite_v1
cargo_n1
vehicle_n1
location_n1
launchpad_n1
location_n1
countdown_n1
agent_n1
place_n1
entity_n1
step_n1
destination_n1
fly_v1
orbit_n1
vehicle_n1
rocket_n1
location_n1
location_n1
agent_n1
launch-a-satellite_v1
cargo_n1
launchpad_n1
destination_n1
before_r1
cargo_n1
satellite_n1
release_v1
before_r1
vehicle_n1
countdown_n1
agent_n1
step_n1
fly_v1
before_r1
entity_n1
agent_n1
destination_n1
release_v1
before_r1
orbit_n1
destination_n1
Representations are Compositional (2)
• Create multiple representations for a single concept
– each encoding a different aspect/viewpoint
• Representations can be combined as needed
Objects Involved
cargo_n1
satellite_n1
Temporal
vehicle_n1
rocket_n1
launch-a-satellite_v1
vehicle_n1
location_n1
launchpad_n1
step_n1
countdown_n1
cargo_n1
satellite_n1
launch-a-satellite_v1
vehicle_n1
agent_n1
fly_v1
countdown_n1
vehicle_n1
rocket_n1
location_n1
launchpad_n1
location_n1
agent_n1
launch-a-satellite_v1
cargo_n1
vehicle_n1
step_n1
countdown_n1
step_n1
fly_v1
before_r1
entity_n1
agent_n1
agent_n1
fly_v1
before_r1
destination_n1
orbit_n1
Scenario Representations
• Goal is to capture “intermediate level” scenes:
– more specific than “Move” or “Launch”
– more general than
• “The launching of meteorological satellites by China
from Taiyuan.”
The
Intermediate
Level
Setting-In-Motion
Launching-A-Satellite
China-Launching-A-Weather-Satellite
Approach
Heavily expectation-based:
• Build knowledge-base of prototypical scenarios
– e.g., “launching a satellite”
• Extract fragments of information from text
– e.g. subject-verb-object tuples
• Find scenario(s) best matching the text
– drives disambiguation and coersion of the text
– scenario provides info unstated in the text
Evidence Extraction from Text
“A Russian cargo ship carrying equipment, food, and fuel
for the Space Station was launched from the cosmodrome on
Monday. The blastoff took place at 11am, and the cargo ship
entered its orbit 10 minutes later.”
(S NIL “launch” “ship”)
(S “ship” “carry” “equipment”)
(S “ship” “carry” “food”)
(S “ship” “carry” “fuel”)
(S “ship” “enter” “orbit”)
• Use SAPIR (bottom-up chart parser)
• “Tuples” extracted from parse tree
– easy to manipulate
– much semantic interpretation deferred
• word senses, semantic relations
Evidence Extraction from Text (cont)
“A Russian cargo ship carrying equipment, food, and fuel
for the Space Station was launched from the cosmodrome on
Monday. The blastoff took place at 11am, and the cargo ship
entered its orbit 10 minutes later.”
(more recent tuple extractor)
(NA "ship" "russian")
(S "ship" "carry" “equipment" ("for" "station"))
(S "ship" "carry" “food" ("for" "station"))
(S "ship" "carry" “fuel" ("for" "station"))
(S NIL "launch" "ship" ("from" "cosmodrome") ("on" "monday")))
(S "ship" "enter" "orbit")
(S "blastoff" "take place" ("at" "id2"))
Approach
Heavily expectation-based:
• Build knowledge-base of prototypical scenarios
– e.g., “launching a satellite”
• Extract fragments of information from text
– e.g. subject-verb-object tuples
• Find scenario(s) best matching the text
– drives disambiguation and coersion of the text
– scenario provides info unstated in the text
Matching the Text with Scenarios
• A syntactic tuple matches a semantic assertion if:
– its words have an interpretation matching the concepts
– the syntactic relation can map to the semantic relation
• Simple scoring function f(# word matches, # tuple matches)
(S “china” “launch” “satellite”)
“launch”
subject
“launch”
direct object
cargo_n1
satellite_n1
“china”
“satellite”
vehicle_n1
rocket_n1
cargo_n1
location_n1
launchpad_n1
location_n1
agent_n1
launch-a-satellite_v1
vehicle_n1
step_n1
countdown_n1
causal_agent_n1
agent_n1
agent_n1
fly_v1
before_r1
destination_n1
orbit_n1
Multiple abstractions may match…
Moving
Tangible-Entity
Launching
Placing-In-Position
Launching-A-Boat
Boat
Artificial-Satellite
Launching-A-Satellite
Rocket-Vehicle
Orbit-Celestial
China’s
Launch of
the FY-1D
meteorologic
al satellite
Illustration
“A Russian cargo ship carrying equipment, food, and fuel
for the Space Station was launched from the cosmodrome on
Monday. The blastoff took place at 11am, and the cargo ship
entered its orbit 10 minutes later.”
(NA "ship" "russian")
(S "ship" "carry" “equipment" ("for" "station"))
(S "ship" "carry" “food" ("for" "station"))
(S "ship" "carry" “fuel" ("for" "station"))
(S NIL "launch" "ship" ("from" "cosmodrome") ("on" "monday")))
(S "ship" "enter" "orbit")
(S "blastoff" "take place" ("at" "id2"))
Illustration
“A Russian cargo ship carrying equipment, food, and fuel
for the Space Station was launched from the cosmodrome on
Monday. The blastoff took place at 11am, and the cargo ship
entered its orbit 10 minutes later.”
(NA "ship" "russian")
(S "ship" "carry" “equipment" ("for" "station"))
(S "ship" "carry" “food" ("for" "station"))
(S "ship" "carry" “fuel" ("for" "station"))
(S NIL "launch" "ship" ("from" "cosmodrome") ("on" "monday")))
(S "ship" "enter" "orbit")
(S "blastoff" "take place" ("at" "id2"))
Score: 24
vehicle_n1
rocket_n1
location_n1
launchpad_n1
location_n1
agent_n1
launch-a-rocket_v1
vehicle_n1
countdown_n1
agent_n1
step_n1
fly_v1
before_r1
entity_n1
agent_n1
destination_n1
release_v1
before_r1
orbit_n1
destination_n1
Issues
Constraints to overcome:
1. Language: Requires just the right text
2. Knowledge: Requires just the right representation
“John entered the restaurant.
John sat down. He ordered
some food…”
enter
But what if…
“John placed his order…”
“John picked up the menu…”
sit
order
1. Language: Matching with scenarios
• “Ideal”: semantic structure mirrors syntactic structure
– each syntactic unit has a direct semantic correlate
(“china” “launch” “satellite”)
entity
agent
launch
cargo
• More usual case: no correlate (no direct match)
• can enumerate types of mismatch
• can enumerate “rewrite rules” to handle them
satellite
5 Classes of Mismatch
1. Substitutability (synonyms, hypernyms)
“the satellite was put in orbit” “the satellite was placed in orbit”
2. Nominalization
“… was launched with approval from the regulator”
 “the regulator approved the launch”
3. Roles
“The State Department was the regulator…”
 “The State Department regulated…”
4. Expansions/contractions
“supplies fuel to”  “fuels”, “enters orbit”  “orbits”
5. Metonymy
“Bush authorized tax cuts…”  “the White House authorized tax
cuts…”
2. Knowledge: What’s in a scenario?
• There is no single scenario representation
– Rather, scenarios have multiple facets
– Often, multiple scenarios are active at once
Human behavior
Selling (advertise, launch, market)
“Amid great expectations, the anti-impotence drug
Viagra was launched in China on Monday with
approvals from the State drug regulator. At a press
conference, Pfizer Inc. announced China had approved
the sale of the drug in the country.”
Regulation (need approval to sell certain things)
2. Knowledge: What’s in a scenario?
Implies:
– Need compositional representations
• detailed scenario needs to be build from multiple, abstract ones
• hence need a mechanism for triggering and integrating them
– Need a lot of knowledge
• Too time-consuming to build by hand!
• much of it may be “mundane”
• Possible sources:
– WordNet (concept-word mappings, hypernyms)
– Extraction from corpora (Schubert-style)
– Dictionary definitions
2. Knowledge: How to build the KB?
cargo_n1
vehicle_n1
satellite_n1
rocket_n1
agent_n1
launch-a-satellite_v1
entity_n1
cargo_n1
vehicle_n1
agent_n1
step_n1
agent_n1
location_n1
launchpad_n1
location_n1
countdown_n1
fly_v1
?
destination_n1
orbit_n1
before_r1
Many of these facts are “mundane”
“satellites can be launched”
“rockets can carry satellites”
“countdowns can be at launchpads”
“rockets can fly”
• Can we extract these facts semi-automatically? yes!
• Can we use them to rapidly assemble models? perhaps
Semi-automatic extraction of facts…
Applying a Schubertinspired method to the
Reuters corpus, we get
(for example)…
Semi-automatic extraction of facts…
Summary
• Text understanding = a modeling activity
– Text suggests scenario models to use
– Models suggest ways of interpreting text
• Approach:
– library of pre-built scenario representations
– NL-processed fragments of input text
– Matching process to find best-matching scenario
• Issues (many!); in particular:
– matching syntax and semantics
– constructing the KB