Lecture20-wsd

Lecture20-wsd - Thisworkislicensed under...

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon
1 CS 479, Section 1: Natural Language Processing Lecture #20: Word Sense Disambiguation Thanks to Dan Klein of UC Berkeley for many of the materials used in this lecture. This work is licensed under a Creative Commons Attribution Share Alike 3.0 Unported License . Announcements Project #2, Part 1 Early: Monday Due: Wednesday Questions? Mid term Exam Prepare your questions Review: Wed. in class Next week: Thu Sat No class on Friday Objectives Review the idea behind joint, generative models. Discuss the challenge of word sense disambiguation and approach it as a classification problem. Explore knowledge sources (“features”) that might help us do a better job of disambiguating word senses. Motivate the need for conditional models, trained discriminatively. Prepare to see maximum entropy training. Recently … Models for text categorization (Naïve Bayes, class conditional LMs) These are Joint / Generative models: Break complex structure down into derivation steps “factors” or “local models” Each step is a categorical choice (at least for our current purposes), conditioned on specified context Estimate those categorical distributions by collecting counts and smoothing Backbone of statistical NLP until very recently Today: motivating conditional maximum entropy, a Conditional model, trained discriminatively . c w 1 w 2 w n . . . START Word Senses Words have multiple distinct meanings, or senses: plant : living plant, manufacturing plant, … title : name of a work, ownership document, form of address, material at the start of a film, … Many levels of sense distinctions Homonymy: totally unrelated meanings (river bank, money bank) Polysemy: related meanings (star in sky, star on tv) Systematic polysemy: productive meaning extensions (organizations to their buildings) or metaphor Sense distinctions can be extremely subtle (or not) Granularity of senses needed depends a lot on the task Why is it important to model word senses?
Background image of page 1

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

View Full DocumentRight Arrow Icon
Image of page 2
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 10/18/2011 for the course CS 479 taught by Professor Ericringger during the Fall '11 term at BYU.

Page1 / 4

Lecture20-wsd - Thisworkislicensed under...

This preview shows document pages 1 - 2. Sign up to view the full document.

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