session10-slides - CMSC 723: Computational Linguistics I...

Info iconThis preview shows pages 1–13. Sign up to view the full content.

View Full Document Right Arrow Icon
Semantic Distance CMSC 723: Computational Linguistics I Session #10 immy Lin Jimmy Lin The iSchool University of Maryland Wednesday, November 4, 2009 Material drawn from slides by Saif Mohammad and Bonnie Dorr
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Progression of the Course | Words z Finite-state morphology z Part-of-speech tagging (TBL + HMM) | Structure z CFGs + parsing (CKY, Earley) z N-gram language models eaning! | Meaning!
Background image of page 2
Today’s Agenda | Lexical semantic relations | WordNet od e t |
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Lexical Semantic Relations
Background image of page 4
What’s meaning? | Let’s start at the word level… | How do you define the meaning of a word? o do you de e t e ea g o a o d | Look it up in the dictionary! ell that really doesn’the lp
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Approaches to meaning | Truth conditional | emantic network Se a t c et o
Background image of page 6
Word Senses | “Word sense” = distinct meaning of a word | ame word, different senses Sa e o d, d e e t se ses z Homonyms (homonymy): unrelated senses; identical orthographic form is coincidental Example: “financial institution” vs. “side of river” for bank z Polysemes (polysemy): related, but distinct senses Example: “financial institution” vs. “sperm bank” z Metonyms (metonymy): “stand in”, technically, a sub-case of polysemy Examples: author for works or author, building for organization, capital city for government | Different word, same sense ynonyms (synonymy) z Synonyms (synonymy)
Background image of page 7

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Just to confuse you… | Homophones: same pronunciation, different orthography, different meaning z Examples: would/wood, to/too/two | Homographs: distinct senses, same orthographic form, ifferent pronunciation different pronunciation z Examples: bass (fish) vs. bass (instrument)
Background image of page 8
Relationship Between Senses | IS-A relationships z From specific to general (up): hypernym (hypernymy) Example: bird is a hypernym of robin z From general to specific (down): hyponym (hyponymy) Example: robin is a hyponym of bird | Part-Whole relationships z wheel is a meronym of car (meronymy) z car is a holonym of wheel (holonymy)
Background image of page 9

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
WordNet Tour Material drawn from slides by Christiane Fellbaum
Background image of page 10
What is WordNet? | A large lexical database developed and maintained at Princeton University | Includes most English nouns, verbs, adjectives, adverbs | Electronic format makes it amenable to automatic manipulation: used in many NLP applications | “WordNets” generically refers to similar resources in other languages
Background image of page 11

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
| Research in artificial intelligence: z How do humans store and access knowledge about concept? z Hypothesis: concepts are interconnected via meaningful relations z Useful for reasoning he ordNet roject started in 986 | The WordNet project started in 1986 z Can most (all?) of the words in a language be represented as a semantic network where words are interlinked by meaning? z
Background image of page 12
Image of page 13
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 11/20/2009 for the course CMSC CMSC723 taught by Professor Jlin during the Fall '09 term at University of Maryland Baltimore.

Page1 / 58

session10-slides - CMSC 723: Computational Linguistics I...

This preview shows document pages 1 - 13. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online