Transcript roles

Semantic Roles and
Disambiguation
CS 4705
Today
•
•
•
•
•
Semantic Networks: Wordnet
Thematic Roles
Selectional Restrictions
Selectional Association
Conceptual Dependency
Semantic Networks
• Used to represent lexical relationships
– e.g. WordNet (George Miller et al)
– Most widely used hierarchically organized lexical
database for English
– Synset: set of synonyms, a dictionary-style definition
(or gloss), and some examples of uses --> a concept
– Databases for nouns, verbs, and modifiers
• Applications can traverse network to find
synonyms, antonyms, hierarchies,...
– Available for download or online use
– http://www.cogsci.princeton.edu/~wn
Using WN, e.g. in Question-Answering
• Pasca & Harabagiu ’01 results on TREC corpus
– Parses questions to determine question type, key words (Who
invented the light bulb?)
– Person question; invent, light, bulb
– The modern world is an electrified world. It might be argued
that any of a number of electrical appliances deserves a
place on a list of the millennium's most significant inventions.
The light bulb, in particular, profoundly changed human
existence by illuminating the night and making it hospitable
to a wide range of human activity. The electric light, one of
the everyday conveniences that most affects our lives, was
invented in 1879 simultaneously by Thomas Alva Edison in
the United States and Sir Joseph Wilson Swan in England.
• Finding key words is not enough
• Compare expected answer ‘type’ to potential
answers
– For questions of type person, expect answer is person
– Identify potential person names (NEs) in passages
retrieved by IR
– Check in WN to find which of these are hyponyms of
instance? Person?
• Or, Consider reformulations of question: Who
invented the light bulb
– For key words in query, look for WN synonyms
– E.g. Who fabricated the light bulb?
– Use this query for initial IR
• Results: improve system accuracy by 147% (on
some question types)
Thematic Roles
• E w,x,y,z {Giving(x) ^ Giver(w,x) ^ Givee(z, x) ^
Given(y,x)}
• A set of roles for each event:
– Agent: volitional causer -- John hit Bill.
– Experiencer: experiencer of event – Bill got a
headache.
– Force: non-volitional causer – The concrete block
struck Bill on the head.
– Theme/patient: most affected participant – John hit Bill.
– Result: end product – Bill got a headache.
– Content: proposition of propositional event – Bill
thought he should take up martial arts.
– Instrument: instrument used -- John hit Bill with a bat
– Beneficiary: qui bono – John hit Bill to avenge his
friend
– Source: origin of object of transfer event – Bill fled
from New York to Timbuktu
– Goal: destination of object -- Bill led from New York to
Timbuktu
• But there are a lot of verbs, with a lot of
frames…
• Framenet encodes frames for many verb
categories
Thematic Roles and Selectional Restrictions
• Selectional restrictions: semantic constraint that a
word (lexeme) imposes on the concepts that go
with it
George hit Bill with
….John/a gun/gusto.
Jim killed his philodendron/a fly/Bill.
?His philodenron killed Jim.
The flu/Misery killed Jim.
•
In practical use:
– Given e.g. a verb and a corpus (plus FrameNet)
– What conceptual roles are likely to accompany it?
– What lexemes are likely to fill those roles?
Assassinate
Give
Imagine
Fall
Serve
Disambiguation via Selectional Restrictions
• “Verbs are known by the company they keep”
– Different verbs select for different thematic roles
wash the dishes (takes washable-thing as patient)
serve delicious dishes (takes food-type as patient)
• Method: another semantic attachment in grammar
– Semantic attachment rules are applied as sentences are
syntactically parsed
VP --> V NP
V serve <theme> {theme:food-type}
– Selectional restriction violation: no parse
• But this means we must:
– Write selectional restrictions for each sense of each
predicate – or use FrameNet
• Serve alone has 15 verb senses
– Hierarchical type information about each argument
(using WordNet)
• How many hypernyms does dish have?
• How many lexemes are hyponyms of dish?
• But also:
– Sometimes selectional restrictions don’t restrict enough
(Which dishes do you like?)
– Sometimes they restrict too much (Eat dirt, worm! I’ll
eat my hat!)
• Can we take a statistical approach?
Selectional Association (Resnik ‘97)
• Selectional Preference Strength: how much does a
predicate tell us about the word class of its argument?
George is a monster, George cooked a steak
– SR(v): How different is p(c), the probability that any direct object
will be a member of some class c, from p(c|v), the probability that
a direct object of a specific verb will fall into that class?
• Estimate conditional probabilities of word senses from a
parsed corpus, counting how often each predicate occurs
with an object argument
– e.g. How likely is dish to be an object of served?
Jane served/V the dish/Obj
• Then estimate the strength of association between each
predicate and the super-class (hypernym) of the argument
in Wordnet
– E.g. For each object of serve (e.g. ragout, Mary, dish)
• Look up all its hypernym classes in WordNet (e.g
dish isa piece of crockery, dish isa food item,…)
• Distribute “credit” for dish (with serve) among all
hypernym classes (≈sense) to which dish belongs
(1/n for n classes)
– Pr(c|v) is estimated at count(c,v)/count(v)
– Why does this work?
• Ambiguous words have many superordinate classes
John served food/the dish/tuna/curry
• There is a common sense among these which gets
“credit” in each instance, eventually dominating the
likelihood score
– How can we use this in wsd?
• Choose the class (sense) of the direct object with the
highest probability, given the verb
Mary served the dish proudly.
• Results:
– Baselines:
• random choice of word sense is 26.8%
• choose most frequent sense (NB: requires senselabeled training corpus) is 58.2%
– Resnik’s: 44% correct with only pred/arg relations
labeled
Schank's Conceptual Dependency
• Eleven predicate primitives represent all
predicates
– Atrans: abstract transfer of possession or ctrl from x to
y
– Ptrans: physical transfer of object from one place to
another
– Mtrans: transfer of mental concepts
– Mbuild: creation of new information w/in entity
– Propel, Move, Ingest, Expel, Speak, Attend
• Objects decomposed into primitive categories and
modifiers
• But few predicates result in very complex
representations of simple things
Ex,y Atrans(x) ^ Actor(x,John) ^ Object(x,Book) ^
To(x,Mary) ^ Ptrans(y) ^ Actor(y,John) ^
Object(y,Book) ^ To(y,Mary)
John gave Mary a Book
Next time
• Chapter 15:5-6
• Homework III (the last, now) assigned