1

POS Tagging: Introduction

Heng Ji

hengji@cs.qc.cuny.eduFeb 2, 2008

Acknowledgement: some slides from Ralph Grishman, Nicolas Nicolov, J&M

2/39

Some Administrative Stuff

Assignment 1 due on Feb 17 Textbook: required for assignments and final

exam

3/39

Outline

Parts of speech (POS) Tagsets POS Tagging

Rule-based tagging Markup Format Open source Toolkits

4/39

What is Part-of-Speech (POS)

Generally speaking, Word Classes (=POS) : Verb, Noun, Adjective, Adverb, Article, …

We can also include inflection: Verbs: Tense, number, … Nouns: Number, proper/common, … Adjectives: comparative, superlative, … …

5/39

Parts of Speech

8 (ish) traditional parts of speech Noun, verb, adjective, preposition, adverb,

article, interjection, pronoun, conjunction, etc Called: parts-of-speech, lexical categories,

word classes, morphological classes, lexical tags...

Lots of debate within linguistics about the number, nature, and universality of these

We’ll completely ignore this debate.

6/39

7 Traditional POS Categories

N noun chair, bandwidth, pacing

V verb study, debate, munch ADJ adj purple, tall, ridiculous ADV adverb unfortunately, slowly, P preposition of, by, to PRO pronoun I, me, mine DET determiner the, a, that, those

7/39

POS Tagging

The process of assigning a part-of-speech or lexical class marker to each word in a collection.

WORD tag

the DETkoala Nput Vthe DETkeys Non Pthe DETtable N

8/39

Penn TreeBank POS Tag Set

Penn Treebank: hand-annotated corpus of Wall Street Journal, 1M words

46 tags Some particularities:

to /TO not disambiguated Auxiliaries and verbs not distinguished

9/39

Penn Treebank Tagset

10/39

Why POS tagging is useful?

Speech synthesis: How to pronounce “lead”? INsult inSULT OBject obJECT OVERflow overFLOW DIScount disCOUNT CONtent conTENT

Stemming for information retrieval Can search for “aardvarks” get “aardvark”

Parsing and speech recognition and etc Possessive pronouns (my, your, her) followed by nouns Personal pronouns (I, you, he) likely to be followed by verbs Need to know if a word is an N or V before you can parse

Information extraction Finding names, relations, etc.

Machine Translation

11/39

Equivalent Problem in Bioinformatics

Durbin et al. Biological Sequence Analysis, Cambridge University Press.

Several applications, e.g. proteins

From primary structure ATCPLELLLD

Infer secondary structure HHHBBBBBC..

12/39

Why is POS Tagging Useful? First step of a vast number of practical tasks Speech synthesis

How to pronounce “lead”? INsult inSULT OBject obJECT OVERflow overFLOW DIScount disCOUNT CONtent conTENT

Parsing Need to know if a word is an N or V before you can parse

Information extraction Finding names, relations, etc.

Machine Translation

13/39

Open and Closed Classes

Closed class: a small fixed membership Prepositions: of, in, by, … Auxiliaries: may, can, will had, been, … Pronouns: I, you, she, mine, his, them, … Usually function words (short common words which

play a role in grammar) Open class: new ones can be created all the time

English has 4: Nouns, Verbs, Adjectives, Adverbs Many languages have these 4, but not all!

14/39

Open Class Words Nouns

Proper nouns (Boulder, Granby, Eli Manning) English capitalizes these.

Common nouns (the rest). Count nouns and mass nouns

Count: have plurals, get counted: goat/goats, one goat, two goats Mass: don’t get counted (snow, salt, communism) (*two snows)

Adverbs: tend to modify things Unfortunately, John walked home extremely slowly yesterday Directional/locative adverbs (here,home, downhill) Degree adverbs (extremely, very, somewhat) Manner adverbs (slowly, slinkily, delicately)

Verbs In English, have morphological affixes (eat/eats/eaten)

15/39

Closed Class Words

Examples:

prepositions: on, under, over, … particles: up, down, on, off, … determiners: a, an, the, … pronouns: she, who, I, .. conjunctions: and, but, or, … auxiliary verbs: can, may should, … numerals: one, two, three, third, …

16/39

Prepositions from CELEX

17/39

English Particles

18/39

Conjunctions

19/39

POS TaggingChoosing a Tagset

There are so many parts of speech, potential distinctions we can draw

To do POS tagging, we need to choose a standard set of tags to work with

Could pick very coarse tagsets N, V, Adj, Adv.

More commonly used set is finer grained, the “Penn TreeBank tagset”, 45 tags PRP$, WRB, WP$, VBG

Even more fine-grained tagsets exist

20/39

Using the Penn Tagset

The/DT grand/JJ jury/NN commmented/VBD on/IN a/DT number/NN of/IN other/JJ topics/NNS ./.

Prepositions and subordinating conjunctions marked IN (“although/IN I/PRP..”)

Except the preposition/complementizer “to” is just marked “TO”.

21/39

POS Tagging

Words often have more than one POS: back The back door = JJ On my back = NN Win the voters back = RB Promised to back the bill = VB

The POS tagging problem is to determine the POS tag for a particular instance of a word.

These examples from Dekang Lin

22/39

How Hard is POS Tagging? Measuring Ambiguity

23/39

Current Performance

How many tags are correct? About 97% currently But baseline is already 90% Baseline algorithm:

Tag every word with its most frequent tag Tag unknown words as nouns

How well do people do?

24/39

Quick Test: Agreement?

the students went to class plays well with others fruit flies like a banana

DT: the, this, thatNN: nounVB: verbP: prepostionADV: adverb

25/39

Quick Test

the students went to class

DT NN VB P NN plays well with others

VB ADV P NN

NN NN P DT fruit flies like a banana

NN NN VB DT NN

NN VB P DT NN

NN NN P DT NN

NN VB VB DT NN

26/39

How to do it? History

1960 1970 1980 1990 2000

Brown Corpus Created (EN-US)1 Million Words

Brown Corpus Tagged

HMM Tagging (CLAWS)93%-95%

Greene and RubinRule Based - 70%

LOB Corpus Created (EN-UK)1 Million Words

DeRose/ChurchEfficient HMMSparse Data

95%+

British National Corpus

(tagged by CLAWS)

POS Tagging separated from

other NLP

Transformation Based Tagging

(Eric Brill)Rule Based – 95%+

Tree-Based Statistics (Helmut Shmid)

Rule Based – 96%+

Neural Network 96%+

Trigram Tagger(Kempe)

96%+

Combined Methods98%+

Penn Treebank Corpus

(WSJ, 4.5M)

LOB Corpus Tagged

27/39

Two Methods for POS Tagging

1. Rule-based tagging (ENGTWOL)

2. Stochastic1. Probabilistic sequence models

HMM (Hidden Markov Model) tagging MEMMs (Maximum Entropy Markov Models)

28/39

Rule-Based Tagging

Start with a dictionary Assign all possible tags to words from the

dictionary Write rules by hand to selectively remove

tags Leaving the correct tag for each word.

29/39

Rule-based taggers

Early POS taggers all hand-coded Most of these (Harris, 1962; Greene and Rubin,

1971) and the best of the recent ones, ENGTWOL (Voutilainen, 1995) based on a two-stage architecture Stage 1: look up word in lexicon to give list of potential

POSs Stage 2: Apply rules which certify or disallow tag

sequences Rules originally handwritten; more recently Machine

Learning methods can be used

30/39

Start With a Dictionary• she: PRP• promised: VBN,VBD• to TO• back: VB, JJ, RB, NN• the: DT• bill: NN, VB

• Etc… for the ~100,000 words of English with more than 1 tag

31/39

Assign Every Possible Tag

NN

RB

VBN JJ VB

PRP VBD TO VB DT NN

She promised to back the bill

32/39

Write Rules to Eliminate Tags

Eliminate VBN if VBD is an option when VBN|VBD follows “<start> PRP”

NN

RB

JJ VB

PRP VBD TO VB DT NN

She promised to back the bill

VBN

33/39

Stage 1 of ENGTWOL Tagging

First Stage: Run words through FST morphological analyzer to get all parts of speech.

Example: Pavlov had shown that salivation …

Pavlov PAVLOV N NOM SG PROPERhad HAVE V PAST VFIN SVO

HAVE PCP2 SVOshown SHOW PCP2 SVOO SVO SVthat ADV

PRON DEM SGDET CENTRAL DEM SGCS

salivation N NOM SG

34/39

Stage 2 of ENGTWOL Tagging

Second Stage: Apply NEGATIVE constraints. Example: Adverbial “that” rule

Eliminates all readings of “that” except the one in “It isn’t that odd”

Given input: “that”If(+1 A/ADV/QUANT) ;if next word is adj/adv/quantifier

(+2 SENT-LIM) ;following which is E-O-S

(NOT -1 SVOC/A) ; and the previous word is not a

; verb like “consider” which

; allows adjective complements

; in “I consider that odd”

Then eliminate non-ADV tagsElse eliminate ADV

35/39

Inline Mark-up

POS Tagginghttp://nlp.cs.qc.cuny.edu/wsj_pos.zip

Input FormatPierre Vinken, 61/CD years/NNS old , will join

the board as a nonexecutive director Nov. 29.

Output FormatPierre/NNP Vinken/NNP ,/, 61/CD years/NNS

old/JJ ,/, will/MD join/VB the/DT board/NN as/IN a/DT nonexecutive/JJ director/NN Nov./NNP 29/CD ./.

36/39

POS Tagging Tools

NYU Prof. Ralph Grishman’s HMM POS tagger (in Java)http://nlp.cs.qc.cuny.edu/jet.zip

http://nlp.cs.qc.cuny.edu/jet_src.zip

http://www.cs.nyu.edu/cs/faculty/grishman/jet/license.html

Demo How it works:

Learned HMM: data/pos_hmm.txt

Source code: src/jet/HMM/HMMTagger.java

37/39

POS Tagging Tools

Stanford tagger (Loglinear tagger ) http://nlp.stanford.edu/software/tagger.shtml

Brill tagger http://www.tech.plym.ac.uk/soc/staff/guidbugm/software/RULE_BASED

_TAGGER_V.1.14.tar.Z tagger LEXICON test BIGRAMS LEXICALRULEFULE

CONTEXTUALRULEFILE YamCha (SVM) http://chasen.org/~taku/software/yamcha/ MXPOST (Maximum Entropy) ftp://ftp.cis.upenn.edu/pub/adwait/jmx/ More complete list at: http://www-nlp.stanford.edu/links/statnlp.html#Taggers

38/39

NLP Toolkits

Uniform CL Annotation Platform UIMA (IBM NLP platform): http://incubator.apache.org/uima/svn.html Mallet (UMASS): http://mallet.cs.umass.edu/index.php/Main_Page MinorThird (CMU): http://minorthird.sourceforge.net/ NLTK: http://nltk.sourceforge.net/

Natural langauge toolkit, with data sets Demo

Information Extraction Jet (NYU IE toolkit)

http://www.cs.nyu.edu/cs/faculty/grishman/jet/license.html Gate: http://gate.ac.uk/download/index.html

University of Sheffield IE toolkit Information Retrieval

INDRI: http://www.lemurproject.org/indri/ Information Retrieval toolkit

Machine Translation Compara: http://adamastor.linguateca.pt/COMPARA/Welcome.html ISI decoder: http://www.isi.edu/licensed-sw/rewrite-decoder/ MOSES: http://www.statmt.org/moses/

39/39

Looking Ahead: Next Class

Machine Learning for POS Tagging: Hidden Markov Model