language understanding & common sense reasoning
Post on 11-Jan-2022
5 Views
Preview:
TRANSCRIPT
Exp 2
Language understanding & common sense reasoningJoshua K Hartshorne • Tobias Gerstenberg • Timothy J. O’Donnell • Joshua B. Tenenbaum
Massachusetts Institute of Technology
MotivationLanguage is massively ambiguous. Interpretation often requires world knowledge & common sense reasoning.
How and why is common sense recruited?
••
Simulate: A beat B and A was strong. If A had not!been strong, would A have beaten B? If not, A’s !strength caused A to beat B.
Details & Intuitions
Framework
message
world speaker’s!experience
speaker’s!knowledge
speaker’s!intentions
utterance
linguistic!knowledge
Goal is to recover information about world. Literal meaning is an intermediate stage. Prior beliefs about world plays key role.
listener
Winograd Schema
(Winograd, 1973)
The city council denied the protesters a !permit because they feared violence.The city council denied the protesters a !permit because they advocated violence.
• Require common sense • Easy to generate • Easy to score
Properties:
(cf Levesque, 2011)
message P(utterance|message)…because the city council feared violence
P(message)
…because the protesters feared violence…because the Red Sox feared violence…because the Dutch feared violence
…
likelylikely
unlikelyunlikely
…
likelyunlikely
very unlikelyvery unlikely
…Note: Current focus is on messages achieved from different interpretations of pronoun.
Conclusions & Future Directions
P(message|utterance) α P(utterance|message) * P(message)Factorization:
Find most likely message!given utterance
need model of world!(& speaker)
Exp 1
P(message) estimated by TurkersExp 1a
A scared B because he jumped out from behind something.
utterance (80 total):
Turkers asked:How likely is it that {A/B} jumping out from behind something would cause A to scare B?
-2 -1 0 1 2model
-5
-4
-3
-2
-1
0
1
2
3
4
5
Hum
an J
udgm
ents
log-odds he = A
model
hum
ans
r=.88
Utterance:The city council denied the protesters a permit because they feared violence.
Rarely use pronouns!to refer to new entities
Exp 1b
Because A scared B, he screamed.
utterance (80 total):
Turkers asked:How likely is it that A scaring B would cause {A/B] to scream?
-2 -1 0 1 2model
-5
-4
-3
-2
-1
0
1
2
3
4
5
Hum
an J
udgm
ents
log-odds he = A
model
hum
ans
r=.73
averageweak strong
strength
BA
B’B’B’
B’
B’
P(message) calculated via simulation over intuitive theoryA B
16 sentences!A {almost/-} {beat/lost to} B in tug-of-war {because/although}!he is {strong/weak}.
A beat B in tug-of-war because he is strong.
Note: Assume counterfactual semantics for “because”. p because q = p and q and (without q, no p). Determine probability by simulation over an intuitive model of tug-of-war (top-right).
Possible messages:! … because A is strong.! … because B is strong.! etc.
averageweak strong
strength
A
B A’A’A’
A’
A’
Simplifying Assumption:
-3 -2 -1 0 1 2 3
-2-1
01
23
log-odds he = A
model-3 -2 -1 0 +1 +2 +3
-2-1
0+1
+2+3
hum
ans
••
• ••••••••••••• r=.92
3 4 5 6 7
3040
5060
7080
B’s strength
model
hum
ans
r=.96•••••••• ••
••••••3 4 5 6 7
2030
4050
6070
80
A’s strength
model
hum
ans
r=.98•••••••• ••••••
••
Simplifications:! Stronger person always wins.! Prototype / soft threshold ! semantics for scalar adjectives.
••
Language comprehension as inference over intuitive model of the speaker explains how common sense affects language processing.
•
Limited need for theory of pronouns per se.•• Can derive pronoun biases (ask me).Productive paradigm for test theories of knowledge (e.g. reasoning about tug-of-war) and semantics (e.g., because=counterfactual).
•
Note: No notion of informativity (yet).
pdf: joshuakhartshorne.org/publications.html
top related