Overview
description
Transcript of Overview
1
Overview
LING 5200Computational Corpus LinguisticsMartha Palmer
LING 5200, 2006 BASED on Kevin Cohen’s LING
52002
What’s a corpus?
McEnery & Wilson: (i) (loosely) any body of text (ii) (most commonly) a body of
machine-readable text (iii) (more strictly) a finite collection
of machine-readable text, sampled to be maximally representable of a language or variety
LING 5200, 2006 BASED on Kevin Cohen’s LING
52003
What’s corpus linguistics?
“the study of language based on examples of ‘real life’ language use” (McEnery & Wilson) A methodology, not a branch of linguistics
Biber et al.: Uses computers “Natural” texts Large & principled collection Both quantitative and qualitative
LING 5200, 2006 BASED on Kevin Cohen’s LING
52004
What was Chomsky’s complaint? Linguistics should model competence not
performance. What are the underlying rules that allow us to generate language?
Context – structuralists believed in collecting linguistic data about a language without taking meaning and communication into consideration.
Mirrors the debate between the rationalists and the empiricists.
But, does Chomsky account for meaning? (see Searle)
LING 5200, 2006 BASED on Kevin Cohen’s LING
52005
Which Linguistic branches can make use of corpus linguistics? Phonetics Phonology Morphology Syntax Semantics Pragmatics
Psycholinguistics Computational Lx Descriptive Lx Historical Lx Sociolinguistics
LING 5200, 2006 BASED on Kevin Cohen’s LING
52006
Corpus linguistics in context
data applications
models
CorpusLinguistics
NaturalLanguageProcessing
ComputationalLinguistics
LING 5200, 2006 BASED on Kevin Cohen’s LING
52007
What’s LING 5200 Corpus Linguistics? Tools Techniques
LING 5200, 2006 BASED on Kevin Cohen’s LING
52008
Overview
Quick intro to Unix A little corpus design Quick tour of corpora and annotation Tools for working with corpora Programming in Python Some software engineering
LING 5200, 2006 BASED on Kevin Cohen’s LING
52009
Why Python?
It works Many advantages It’s a bona fide programming language You’ll need it for CSCI 5832
LING 5200, 2006 BASED on Kevin Cohen’s LING
520010
Administrative things
Textbooks – Unix, Python Office hours – Mon 5-6, Tues 1-2 verbs.colorado.edu/mpalmer/ling5200 Prerequisites - none Grades – homeworks/project Accounts on babel
LING 5200, 2006 BASED on Kevin Cohen’s LING
520011
Logging on for the first time
First thing to do: change your password. passwd Give it your current password, then
your new password. Repeat the new one. (to catch typos)
LING 5200, 2006 BASED on Kevin Cohen’s LING
520012
Connecting with another computer
ssh –l your_name babel.colorado.edu
You are prompted to log in.
LING 5200, 2006 BASED on Kevin Cohen’s LING
520013
Logging on for the first time, again First thing to do: change your password. passwd Give it your current password, then
your new password. Repeat the new one. (Why?)
LING 5200, 2006 BASED on Kevin Cohen’s LING
520014
Where am I?
Type pwd You see something like this:
/home/mpalmer
LING 5200, 2006 BASED on Kevin Cohen’s LING
520015
What's that mean??
/
bin home etc usr
LING 5200, 2006 BASED on Kevin Cohen’s LING
520016
Important directories
/
bin home etc usr
mpalmer
ling5200
RCS
local
bin
LING 5200, 2006 BASED on Kevin Cohen’s LING
520017
Important directories
/
bin home etc usr
mpalmer
ling5200
RCS
local
bin/home/mpalmer/ling5200
LING 5200, 2006 BASED on Kevin Cohen’s LING
520018
Important directories
/
bin home etc usr
mpalmer
ling5200
RCS
local
bin/home/mpalmer/ling5200 /usr/local/bin
LING 5200, 2006 BASED on Kevin Cohen’s LING
520019
Navigating directories
ls to list contents, cd to change directory Directories are just like windows folders
/home/mpalmer shortcut: ~ “the directory above this one”: .. “this directory”: .
LING 5200, 2006 BASED on Kevin Cohen’s LING
520020
What's in the neighborhood?
Type ls You see a list of directories and files
that are contained within the current directory
Homework_1.txttoolsbuglog.txt
LING 5200, 2006 BASED on Kevin Cohen’s LING
520021
I'd like to go somewhere else…
Type pwd Type cd Where are you? Type cd .. Where are you? Type cd your_user_id Where are you?
LING 5200, 2006 BASED on Kevin Cohen’s LING
520022
Unix is a verb-initial language
cd ..
"go" where to go
LING 5200, 2006 BASED on Kevin Cohen’s LING
520023
Unix is a verb-initial language
cd
"go"If no argument, I assume you mean "home"
LING 5200, 2006 BASED on Kevin Cohen’s LING
520024
Making a new directory
Type cd Type ls Type mkdir ling5200 Type ls Go to the directory you just made (how?) Type pwd Type ls