DisambiguationThe ProblemSpecific ProblemsPossible SolutionsMain ApproachesSelectional RestrictionsSelectional Restrictions – Thematic RolesSelectional Restrictions – Polysemy and HomonymsSelectional Restrictions Solve Obvious Problems but Have LimitationsGive Up on Knowledge – Just Count ThingsJust Count Things - InputJust Count Things – ChoosingJust Count Things - TrainingJust Count Things in a DictionaryLimitations of the Dictionary MethodCounting Things for the Other TasksDisambiguationRead J & M Chapter 17.1 – 17.2The 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.Specific Problems•Choosing the right meaning for each word.•Mapping arguments to thematic roles.•Resolving parsing ambiguities.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 possibilitiesMain Approaches•Drive the process with a knowledge base:•Selectional restrictions•Preference semantics/selectional association•Count the wordsSelectional Restrictions•Mapping to Thematic roles:•They serve meatloaf on Tuesdays.•American serves Dallas and Austin.•O’s serves breakfast.•Which pubs serve minors?•Choosing the right meaning:•John serves with a backhand.Selectional Restrictions – Thematic Roles1. They serve meatloaf on Tuesdays.2. American serves Dallas and Austin.3. O’s serves breakfast.4. Which pubs serve minors?Using FOPC:.1 z y x Isa(x, serve1) Agent(x, y) AE(x, z) Isa(z, Food)(Note that if meatloaf Isa Food, this will work..2 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.Selectional Restrictions – Polysemy and HomonymsThe spring fed the creek.Selectional Restrictions Solve Obvious Problems but Have LimitationsI want to eat seafood.I want to eat someplace cheap.I want to eat Italian.What kind of dishes do you like? Restrictions aren’tstrong enoughJohn was green with envy. Simple class info notalways enoughThe circus performer swallowed fire. Unusual but trueIt Was Just As The Trees Whispered Poetic Washington refused to comment. MetonymyCall me on my cell. Constant changes – robustnessGive Up on Knowledge – Just Count ThingsExample – Word Sense Disambiguation An electric guitar and a bass player stand off to one side.Just Count Things - InputInput: 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]Just Count Things – ChoosingAn algorithm: The Naïve Bayes Classifier)|(maxargˆVsPsSs)()()|(maxargVPsPsVPSsWe can’t collect enough data to use whole feature vectors, so we assume that the words are independent and break it up:njjsvPsVP1)|()|(njjSssvPsPs1)|()(maxargˆP(s) is the same throughout the vector and P(V) is the same for all candidates, given the vector, soJust Count Things - TrainingTraining 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.Just Count Things in a DictionaryThe 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 leaves2 waste away through sorrow or illnesscone 1 solid body which narrows to a point2 something of this shape whether solid or hollow3 fruit of certain evergreen treesWe compare the three definitions of cone to the words in the definitions for pine. We choose 3.Limitations of the Dictionary MethodDefinitions are too short.What if we don’t know which sense to use for the surrounding words? Sometimes this is fixed in dictionaries by the use of subject codes. Dictionaries aren’t always up to date either, although they get updated much more often than they used to. Example: Look at Longman’s:http://www.longman.com/dictionaries/webdictionary.htmlFor cell, instant messageCounting 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:
View Full Document
Unlocking...