Title: Temporal Relations in Visual Semantics of Verbs
1Temporal Relations inVisual Semantics of Verbs
- Minhua Eunice Ma and Paul Mc Kevitt
- School of Computing and Intelligent Systems
- Faculty of Engineering
- University of Ulster, Magee
- Derry/Londonderry, N. Ireland
2Background CONFUCIUS (intelligent storytelling
system)
story in natural language
Storywriter /playwright
speech (dialogue)
User /story listener
movie/drama script
CONFUCIUS
3D animation
non-speech audio
tailored menu for script input
- To interpret natural language stories and to
extract conceptual semantics from natural
language - To generate 3D animation and virtual worlds
automatically from natural language - To integrate 3D animation with speech and
non-speech audio for presenting multimodal stories
3Previous research
- Temporal relations
- Allens interval relations
- Application in story-based interactive systems
- Temporal relations in technical orders domain
(Badler et al., 1997)
- Related research in NLP
- Sentence level temporal analysis
- Lexical vs. post-lexical temporal relations
- Lexical semantics
4Allens interval relations
5NLP in CONFUCIUS
6Verb entailments
Verb entailment fixed truth relation between
verbs with entailment given by part of lexical
meaning, i.e. one verb entails another The
implication logic relationship if p then q (p?q)
7Troponym
- Elaborates manner of base verb (Fellbaum, 1998)
- Examples trot-walk (fast), gulp-eat
(quickly)
EVENT
go (move)
cause
other action predicates
run
walk
climb
jump
manner-of-motion verbs
limp
stride
swagger
trot
8Temporal relations in verb entailment
p,m,o,s,f-1, may also represent temporal
relation between pair of cognate verbs and state
of corresponding adjectives e.g. shorten-short,
beautify-beautiful, clarify-clear
9Representing procedural events
- Arguments of EVENT
- EVENT
- agent
- theme
- space/time
- manner
- instrument
- precondition
- subactivities
- result
- Relationship between definiendum verb and its
subactivities - act()-
- subact1(),
- subacti(), .
- subacti R act, i?N, R?d,s,f,?
10Comparison with Badlers temporal constraints
- Badlers temporal constraints
- (technical orders domain)
- Sequential
- Parallel
- Jointly parallel
- Independently parallel
- While parallel
- Interval relations
- p,m
- s,s-1,?
- (act1 s,s-1,? act2) p,m act3
- f,f-1,?
- act_domt s-1,f-1,? act_indomt
- compositional (e.g. jointly parallel) all 5
constraints are disjunctions of several interval
relations - consider other factors such as dominancy of
action (e.g. while parallel) - domain-specific
11Comparison with Badlers temporal constraints
- Badlers temporal constraints
- (technical orders domain)
- Sequential
- Parallel
- Jointly parallel
- Independently parallel
- While parallel
- Interval relations
- p,m
- s,s-1,?
- (act1 s,s-1,? act2) p,m act3
- f,f-1,?
- act_domt s-1,f-1,? act_indomt
- compositional (e.g. jointly parallel) all 5
constraints are disjunctions of several interval
relations - consider other factors such as dominancy of
action (e.g. while parallel) - domain-specific
12Comparison with Badlers temporal constraints
- Badlers temporal constraints
- (technical orders domain)
- Sequential
- Parallel
- Jointly parallel
- Independently parallel
- While parallel
- Interval relations
- p,m
- s,s-1,?
- (act1 s,s-1,? act2) p,m act3
- f,f-1,?
- act_domt s-1,f-1,? act_indomt
- compositional (e.g. jointly parallel) all 5
constraints are disjunctions of several interval
relations - consider other factors such as dominancy of
action (e.g. while parallel) - domain-specific
13Comparison with Badlers temporal constraints
- Badlers temporal constraints
- (technical orders domain)
- Sequential
- Parallel
- Jointly parallel
- Independently parallel
- While parallel
- Interval relations
- p,m
- s,s-1,?
- (act1 s,s-1,? act2) p,m act3
- f,f-1,?
- act_domt s-1,f-1,? act_indomt
- compositional (e.g. jointly parallel) all 5
constraints are disjunctions of several interval
relations - consider other factors such as dominancy of
action (e.g. while parallel) - domain-specific
14Comparison with Badlers temporal constraints
- Badlers temporal constraints
- (technical orders domain)
- Sequential
- Parallel
- Jointly parallel
- Independently parallel
- While parallel
- Interval relations
- p,m
- s,s-1,?
- (act1 s,s-1,? act2) p,m act3
- f,f-1,?
- act_domt s-1,f-1,? act_indomt
- compositional (e.g. jointly parallel) all 5
constraints are disjunctions of several interval
relations - consider other factors such as dominancy of
action (e.g. while parallel) - domain-specific
15Achievement vs. accomplishment events
- Achievement events (Vendler, 1967) e.g. find,
arrive, die - punctual events occuring at single moment
- definite time instants
- never hold over intervals
- Why use interval relations instead of point-based
relations? - Pragmatic reasons (Verkuyl, 1993)
- Ontological reasons (Pinon, 1997)
- Practical reason for language visualisation
- achievement events depend on existence of context
- context visual definitions ? intervals
find()- search(), eyesFixedOn().
arrive()- go(), stopAtDestination().
16Temporal relations of lexical causatives
- Visual definitions of causative verbs (e.g.
kill) must subsume result states (stative
verbs) (e.g. die) - Represent distinction between
- launching causatives causation of inception of
motion - entraining causatives continuous causation of
motion
disjunction set of interval relations between
cause and effect adequate to define difference
s,p,m,o (launching) ,f-1 (entraining)
17Lexical and post-lexical repetition
- Post-lexical level repetition
- e.g. Roses come into bloom once a year.
- I visit the school every day.
- or marked by again", "continues to", "a second
time - Lexical level repetition
- Represent periodical repetition of subactivities
- walk()- step()R.
- hammer()- hit()R.
- Morphological prefix "re-"
18Categories of action verb
- 2.2.1. Action verbs
- 2.2.1.1. Movement or partial movement
- 2.2.1.1.1. Biped kinematics, e.g. go, walk,
jump, swim, climb - 2.2.1.1.2. Face expressions, e.g. laugh, angry
- 2.2.1.1.3. Lip movement, e.g. speak, say, sing,
tell - 2.2.1.2. Lexical causatives
- 2.2.1.2.1. Concerning single object, e.g. push,
kick, bring, open - 2.2.1.2.2. Concerning multiple objects
- 2.2.1.2.2.1. Bitransitive verbs, e.g. give,
sell, show - 2.2.1.2.2.2. Transitive verbs with object
implicit instrument/goal/theme, - e.g. cut, write, butter, pocket
- 2.2.1.3. Verbs without distinct visualization
when out of context - 2.2.1.3.1. trying verbs try, attempt, succeed,
manage - 2.2.1.3.2. helping verbs help, assist
- 2.2.1.3.3. letting verbs allow, let, permit
- 2.2.1.3.4. create/destroy verbs build, create,
assemble, construct, break, destroy - 2.2.1.3.5. verbs whose visualization depends on
their objects, - e.g. play (harmonica/football), make (the
bed/trouble/a phone call), fix (a drink/a lock) - 2.2.1.4. High level behaviours (routine events)
19Lexical Visual Semantic Representation
- Lexical Visual Semantic Representation (LVSR)
- necessary semantic representation between
- 3D model and language syntax
- LVSR based on Jackendoffs LCS adapted to task of
language visualization (enhancement with Schanks
scripts) - Interval relations represent temporal
relationship between subactivities of complex
actions in LVSR - e.g.
- The waiter approached me Can I help you?
Sir. - 3D animation
- John walked towards the house.
- 3D animation
- Nancy ran across the field.
- 3D animation
20Conclusion
- Temporal relation is a crucial issue in
modelling action verbs, their procedures,
contexts, presupposed and result states - Temporal relation within verb semantics (lexical
level) - Semantic representation of verbs with temporal
information based on Allens interval logic
21Future work
- Quantitative factor
- Action composition for simultaneous activities
- Verbs concerning multiple characters
synchronization coordination - Character can start a task when another signals
pre-conditions are ready - Two or more characters cooperate in shared task