CSCI 5832 Natural Language Processing Lecture 22 Jim Martin 01 14 19 CSCI 5832 Spring 2006 1 Today 4 12 More on meaning Lexical Semantics A seemingly endless set of random facts about words 01 14 19 CSCI 5832 Spring 2006 2 Meaning Traditionally meaning in language has been studied from three perspectives The meaning of a text or discourse The meanings of individual sentences or utterances The meanings of individual words We started in the middle now we ll move down to words and then back up to discourse 01 14 19 CSCI 5832 Spring 2006 3 Word Meaning We didn t assume much about the meaning of words when we talked about sentence meanings Verbs provided a template like predicate argument structure Number of arguments Position and syntactic type Names for arguments Nouns were practically meaningless constants There has be more to it than that 01 14 19 CSCI 5832 Spring 2006 4 Theory From the theory side we ll proceed by looking at The external relational structure among words The internal structure of words that determines where they can go and what they can do 01 14 19 CSCI 5832 Spring 2006 5 Applications We ll take a look at Enabling resources WordNet FrameNet Enabling technologies Word sense disambiguation Word based applications Search engines But first the facts and some theorizing 01 14 19 CSCI 5832 Spring 2006 6 Preliminaries What s a word Types tokens stems roots inflected forms etc Ugh Lexeme An entry in a lexicon consisting of a pairing of a base form with a single meaning representation Lexicon A collection of lexemes 01 14 19 CSCI 5832 Spring 2006 7 Complications Homonymy Lexemes that share a form Phonological orthographic or both Clear example Bat wooden stick like thing vs Bat flying scary mammal thing 01 14 19 CSCI 5832 Spring 2006 8 Problems for Applications Text to Speech Same orthographic form but different phonological form Content vs content Information retrieval Different meanings same orthographic form QUERY router repair Translation Speech recognition 01 14 19 CSCI 5832 Spring 2006 9 Homonymy The problematic part of understanding homonymy isn t with the forms it s the meanings An intuition with true homonymy is coincidence It s a coincidence in English that bat and bat mean what they do Nothing particularly important would happen to anything else in English if we used a different word for flying rodents 01 14 19 CSCI 5832 Spring 2006 10 Polysemy The case where a single lexeme has multiple meanings associated with it Most words with moderate frequency have multiple meanings The actualy number of meanings is related to a word s frequency Verbs tend more to polysemy Distinguishing polysemy from homonymy isn t always easy or necessary 01 14 19 CSCI 5832 Spring 2006 11 Polysemy Consider the following WSJ example While some banks furnish sperm only to married women others are less restrictive Which sense of bank is this Is it distinct from homonymous with the river bank sense How about the savings bank sense 01 14 19 CSCI 5832 Spring 2006 12 Polysemy Tests ATIS examples Which flights serve breakfast Does America West serve Philadelphia Does United serve breakfast and San Jose 01 14 19 CSCI 5832 Spring 2006 13 Relations Inter word relations Synonymy Antonymy Hyponymy Metonymy 01 14 19 CSCI 5832 Spring 2006 14 Synonyms There really aren t any Maybe not but people think and act like there are so maybe there are One test Two lexemes are synonyms if they can be successfully substituted for each other in all situations 01 14 19 CSCI 5832 Spring 2006 15 Synonyms What the heck does successfully mean Preserves the meaning But may not preserve the acceptability based on notions of politeness slang register genre etc Example Big and large That s my big brother That s my large brother 01 14 19 CSCI 5832 Spring 2006 16 Hyponymy A hyponymy relation can be asserted between two lexemes when the meanings of the lexemes entail a subset relation Since dogs are canids Dog is a hyponym of canid and Canid is a hypernym of dog 01 14 19 CSCI 5832 Spring 2006 17 Resources There are lots of lexical resources available these days Word lists On line dictionaries Corpora The most ambitious one is WordNet A database of lexical relations for English Versions for other languages are under development 01 14 19 CSCI 5832 Spring 2006 18 WordNet Some out of date numbers 01 14 19 CSCI 5832 Spring 2006 19 WordNet The critical thing to grasp about WordNet is the notion of a synset it s their version of a sense or a concept Example table as a verb to mean defer postpone hold over table shelve set back defer remit put off For WordNet the meaning of this sense of table is this list 01 14 19 CSCI 5832 Spring 2006 20 WordNet Relations 01 14 19 CSCI 5832 Spring 2006 21 WordNet Hierarchies 01 14 19 CSCI 5832 Spring 2006 22 Break Quiz Average was 44 out of 55 SD was 7 Most popular month is May 01 14 19 CSCI 5832 Spring 2006 23 Break 1 May 2 True 3 Treebank rules Nom Noun Nom Noun Noun Nom Noun Noun Noun 4 5 6 7 False Next slide A flight from Boston to Miami Count and divide 01 14 19 CSCI 5832 Spring 2006 24 Break An evening Det flight NP NP Nom Noun Nom Nom Noun 01 14 19 CSCI 5832 Spring 2006 25 Break An evening Det flight NP NP Nom Noun Nom Nom Noun 01 14 19 CSCI 5832 Spring 2006 26 Inside Words Thematic roles more on the stuff that goes on inside verbs Qualia theory what must be going inside nouns they re not really just constants 01 14 19 CSCI 5832 Spring 2006 27 Inside Verbs Semantic generalizations over the specific roles that occur with specific verbs I e Takers givers eaters makers doers killers all have something in common er They re all the agents of the actions We can generalize or try to across other roles as well 01 14 19 CSCI 5832 Spring 2006 28 Thematic Roles 01 14 19 CSCI 5832 Spring 2006 29 Thematic Role Examples 01 14 19 CSCI 5832 Spring 2006 30 Why Thematic Roles It s not the case that every verb is unique and has to introduce unique labels for all of its roles thematic roles let us specify a fixed set of roles More importantly it permits us to distinguish surface level shallow semantics from deeper semantics 01 14 19 CSCI 5832 Spring 2006 31 Example Honestly from the WSJ He melted her reserve with a huskyvoiced paean to her eyes If we label the constituents He and reserve as the Melter and Melted then those labels lose any meaning they might have had literally If we make them Agent and Theme then we don t have the same problems 01 14 19 CSCI 5832 Spring 2006 32 Tasks Shallow semantic analysis
View Full Document
Unlocking...