Title: A computational model of sentence and story comprehension'
1A computational model of sentence and story
comprehension.
- Stefan Frank
- Nijmegen Institute for Cognition and Information
- In cooperation with
- Mathieu Koppen (NICI)
- Leo Noordman (UvT)
- Wietske Vonk (MPI for Psycholinguistics and KUN)
2Story comprehension
- The first lines of the Jip en Janneke (Bob and
Jilly) story Going to the shoemaker - My shoe has a hole, Bob says.
- My foot is wet.
- In order to comprehend this pair of sentences,
inferences need to be made - Bobs foot is wet because his shoe has a hole and
he walked through a puddle.
3Some discourse-comprehension theory
- Kintsch Van Dijk (1978) The comprehension of a
text leads to three distinct levels of mental
representation
- The surface text (literal wording)
- The textbase (propositional structure)
- The situation model (what happens in the text)
4An experiment
- Fletcher Chrysler (1990)
- Subjects read short stories.
- They were given a sentence of each story, without
the last word. - They had to recognize which of two given words
was the original last word of the sentence.
5Results
6My shoe has a hole, Bob says.
My foot is wet.
Surface
7The Distributed Situation Space model Frank,
Koppen, Noordman, Vonk, 2003
- The DSS model simulates how readers make
knowledge-based inferences during story
comprehension. - It represents the story at the situational level
only. - Stories take place in a microworld.
8Bob and Jillys microworld
Basic events 1. the sun shines2. it
rains 3. Bob is outside4. Jilly is
outside 5. Bob and Jilly play soccer6. Bob and
Jilly play hide-and-seek7. Bob plays a computer
game8. Jilly plays a computer game9. Bob plays
with the dog10. Jilly plays with the dog 11. Bob
is tired12. Jilly is tired 13. Bob
wins14. Jilly wins
9Microworld rules
- For instance
- Soccer can only be played outside, computer games
only inside. - Someone can only win if Bob and Jilly play
soccer, hide-and-seek, or both play a computer
game. - Whoever is tired, is less likely to win.
10The microworld description
- A temporal sequence of 250 situations, obeying
the mircroworld rules. - In all situations, each basic event is either
true or false. - World knowledge and representations of microworld
events are extracted from the microworld
description .
11Representing situations
A Self-Organizing Map (SOM) was trained on the
microworld description
bob is outside
jilly is outside
bj play soccer
bj play hide-and-seek
12Combining situations
bob is outside
not
bob is inside
?
jilly is outside
and
jilly plays with the dog outside
jilly plays with the dog
?
bj play soccer
bj play hide-and-seek
or
13An inference example
Inferences result from applying world knowledge
about causal/temporal relations.
It rains. Bob and Jilly are playing hide-and-seek.
bob and jilly play hide-and-seek
it rains
14Another example
- 1. The sun shines and Bob and Jilly play soccer.
- 2. Bob is tired, but Jilly isnt.
- 3. Next, one of them wins.
- Who wins?
- What are they playingat that moment?
15General results
- An inference takes place if
- it is likely given the story and world knowledge
- it leads to increased coherence
- processing is sufficiently deep
which is in accordance with Vonk Noordmans
(1990) theory that inferencing depends on
- the availability of relevant knowledge
- the contribution to the texts coherence
- the readers goals.
16Model results and experimental data
- Processing a less related statement leads to
longer processing times and more inference. - Increasing depth-of-processing results in longer
processing times and more inference. - Story retention recall percentages and
intrusions - Ambiguous pronoun resolution reading times and
error rates
17Conclusions
- The DSS model
- simulates the making of knowledge-based
inferences - predicts experimental data
- supports Vonk Noordmans theory of inference
- uses only a situation-level representation.
But how about the other two levels surface text
and textbase?
18Text input to the DSS model
- Situations in the microworld can be described
using a microlanguage. - A neural network is trained to transform
microlanguage sentences into the corresponding
situational representation. - The existence of a textbase-level representation
is not assumed.
19A simple model of sentence comprehension
Bob, and, Jilly, play, soccer
Surface
.
During training, intermediate representations of
sentences develop in the hidden layer.
hidden layer
Textbase?
Situation
bob and jilly play soccer
20Comparing the intermediate representations
- The intermediate representation of a sentence is
a vector of activation values. - The euclidean distance between two vectors is a
measure for the dissimilarity between the
corresponding sentences - Surface text difference Bob and Jilly play
soccer vs. Jilly and Bob play soccer - Textbase differenceBob plays soccer vs. Jilly
plays soccer - Situation differenceBob plays with the
dog vs. Jilly plays with the dog
21Fletcher Chryslers (1990) results
22Model results
The model predicts Fletcher Chryslers results
within a single level of representation.
23Conclusions
- The textbase may be just an intermediate level
that is useful for constructing the situational
representation. - It does not consist of propositional structures.
- Intermediate representations combine properties
of surface text, proposition, and situation. - But
- This simple model cannot predict reading times.
- And it lacks an effect of world knowledge on
sentence processing.
24A more complex model of sentence comprehension
Bob, and, Jilly, play, soccer
.
Surface
Fully recurrent network
Textbase?
Interactive connections
Situation