Disambiguation

1
Disambiguation
Read J M Chapter 17.1 17.2
2
The Problem

• Washington Loses Appeal on Steel Duties
• Sue caught the bass with the new rod.
• Sue played the bass with the awesome sound.
• Sue cooked.
• The potatoes cooked.
• I saw a spring flying through the air.

3
Specific Problems

• Choosing the right meaning for each word.
• Mapping arguments to thematic roles.
• Resolving parsing ambiguities.

4
Possible Solutions

• Integrate the use of semantic knowledge into
  parsing.
• Extreme approach semantic grammars.
• Build syntactic constituents and pass them to
  semantics for evaluation. Reject ill formed ones
  or simply rank order them by likelihood.
• Build a meaning representation of an entire
  sentence and attempt to integrate it into the
  larger context.
• Pro can use larger context when local
  information is not enough
• Con explosion in number of possibilities

5
Main Approaches

• Drive the process with a knowledge base
• Selectional restrictions
• Preference semantics/selectional association
• Count the words

6
Selectional Restrictions

• Mapping to Thematic roles
• They serve meatloaf on Tuesdays.
• American serves Dallas and Austin.
• Os serves breakfast.
• Which pubs serve minors?
• Choosing the right meaning
• John serves with a backhand.

7
Selectional Restrictions Thematic Roles

• They serve meatloaf on Tuesdays.
• American serves Dallas and Austin.
• Os serves breakfast.
• Which pubs serve minors?
• Using FOPC
• ?z ?y ?x Isa(x, serve1) ? Agent(x, y) ? AE(x, z)
  ? Isa(z, Food)
• (Note that if meatloaf Isa Food, this will work.
• ?z ?y ?x Isa(x, serve2) ? Agent(x, y) ? AE(x, z)
  ? Isa(z, Location)
• Or we can skip the full power of FOPC and just
  search in a hyponym structure such as WordNet.

8
Selectional Restrictions Polysemy and Homonyms
The spring fed the creek.
9
Selectional Restrictions Solve Obvious Problems
but Have Limitations
I want to eat seafood. I want to eat someplace
cheap. I want to eat Italian. What kind of dishes
do you like? Restrictions arent strong
enough John was green with envy. Simple class
info not always enough The circus performer
swallowed fire. Unusual but true It Was Just As
The Trees Whispered Poetic Washington refused
to comment. Metonymy Call me on my
cell. Constant changes robustness
10
Give Up on Knowledge Just Count Things
Example Word Sense Disambiguation An
electric guitar and a bass player stand off to
one side.
11
Just Count Things - Input
Input Typically a feature vector that represents
co-occurrence or collocation facts. Example
An electric guitar and a bass player stand off to
one side. A collocation vector guitar, NN1,
and , CJC, player, NN1, stand, VVB A
co-occurrence vector First, look at texts
containing the target word and find the n most
frequent content words. Use these as the
features. So we might use the following
fishing, big, sound, player, fly, rod,
pound, double runs, playing, guitar,
band producing the vector 0, 0, 0, 1, 0, 0,
0, 0, 0, 0, 1, 0
12
Just Count Things Choosing
An algorithm The Naïve Bayes Classifier
We cant collect enough data to use whole feature
vectors, so we assume that the words are
independent and break it up
P(s) is the same throughout the vector and P(V)
is the same for all candidates, given the vector,
so
13
Just Count Things - Training

• Training the classifier What do we need?
• Prior probabilities for each of the word senses.
• Probabilities for each feature given some
  particular sense. To get these, we need to start
  with a sense-tagged corpus.
• So this is an example of a supervised learning
  method.

14
Just Count Things in a Dictionary
The advantage Dictionaries already exist for
other reasons so if we can use them, we can avoid
hand tagging a large corpus. Example (from Lesk)
choose the correct meaning for cone in pine
cone pine 1 kinds of evergreen tree with
needle-shaped leaves 2 waste away through sorrow
or illness cone 1 solid body which narrows to a
point 2 something of this shape whether solid or
hollow 3 fruit of certain evergreen trees We
compare the three definitions of cone to the
words in the definitions for pine. We choose 3.
15
Limitations of the Dictionary Method
Definitions are too short. What if we dont know
which sense to use for the surrounding words?
Sometimes this is fixed in dictionaries by the
use of subject codes. Dictionaries arent always
up to date either, although they get updated much
more often than they used to. Example Look at
Longmans http//www.longman.com/dictionaries/web
dictionary.html For cell, instant message
16
Counting Things for the Other Tasks

• Mapping arguments to thematic roles.
• Resolving parsing ambiguities.
• Use the same techniques but we need an
  appropriate set of features and a training set.
• Example http//acl.ldc.upenn.edu/P/P00/P00-1014.p
  df