CSA2050: Introduction to Computational Linguistics Part of Speech (POS) Tagging II

Download Report

Transcript CSA2050: Introduction to Computational Linguistics Part of Speech (POS) Tagging II

CSA2050:
Introduction to Computational
Linguistics
Part of Speech (POS) Tagging II
Transformation Based Tagging
 Brill (1995)

Transformation-Based Tagging


A combination of rule-based and stochastic
tagging methodologies:
 like the rule-based tagging because rules are
used to specify tags in a certain environment;
 like stochastic tagging, because machine
learning is used.
 uses Transformation-Based Learning (TBL)
Input:
 tagged corpus
 dictionary (with most frequent tags)
April 2005
CLINT Lecture IV
2
Transformation Based Error
Driven Learning
unannotated
text
initial
state
annotated
text
TRUTH
transformation
rules
diagram after Brill (1996)
April 2005
learner
CLINT Lecture IV
3
TBL Requirements




Initial State Annotator
List of allowable transformations
Scoring function
Search strategy
April 2005
CLINT Lecture IV
4
The Basic Algorithm


Label every word with its most likely tag
Repeat the following until a stopping
condition is reached.




Examine every possible transformation, selecting
the one that results in the most improved tagging
Retag the data according to this rule
Append this rule to output list
Return output list
April 2005
CLINT Lecture IV
5
Transformation-Based Tagging
Basic Process:
Set the most probable tag for each word as a
start value, e.g. tag all “race” with NN
P(NN|race) = .98
P(VB|race) = .02
The set of possible transformations is limited




April 2005
by using a fixed number of rule templates,
containing slots and
allowing a fixed number of fillers to fill the slots
CLINT Lecture IV
6
Rule Templates
- triggering environments
Schema ti-3
1
2
3
4
5
6
7
8
9
April 2005
ti-2
ti-1
ti
*
*
*
*
*
*
*
*
*
CLINT Lecture IV
ti+1
ti+2
ti+3
7
Rule Types and Instances
Brill’s Templates
• Each rule begins with change tag a to tag b
• The variables a,b,z,w range over POS tags
• All possible variable substitutions are considered
April 2005
CLINT Lecture IV
8
Examples of learned rules
April 2005
CLINT Lecture IV
9
TBL: Remarks
Execution Speed: TBL tagger is slower than
HMM approach.
 Learning Speed is slow: Brill’s implementation
over a day (600k tokens)
BUT …



April 2005
Learns small number of simple, nonstochastic rules
Can be made to work faster with Finite
State Transducers
CLINT Lecture IV
10
Tagging Unknown Words
New words added to (newspaper) language
20+ per month
Plus many proper names …
Increases error rates by 1-2%
Methods







April 2005
Assume the unknowns are nouns.
Assume the unknowns have a probability
distribution similar to words occurring once in the
training set.
Use morphological information, e.g. words
ending with –ed tend to be tagged VBN.
CLINT Lecture IV
11
Evaluation

The result is compared with a manually
coded “Gold Standard”



Typically accuracy reaches 95-97%
This may be compared with the result for a
baseline tagger (one that uses no context).
Important: 100% accuracy is impossible even
for human annotators.
April 2005
CLINT Lecture IV
12
A word of caution


95% accuracy: every 20th token wrong
96% accuracy: every 25th token wrong



an improvement of 25% from 95% to 96% ???
97% accuracy: every 33th token wrong
98% accuracy: every 50th token wrong
April 2005
CLINT Lecture IV
13
How much training data is
needed?




When working with the STTS (50 tags) we
observed
a strong increase in accuracy when testing
on 10´000, 20´000, …, 50´000 tokens,
a slight increase in accuracy when testing on
up to 100´000 tokens,
hardly any increase thereafter.
April 2005
CLINT Lecture IV
14
Summary



Tagging decisions are conditioned on a wider
range of events that HMM models mentioned
earlier. For example, left and right context
can be used simultaneously.
Learning and tagging are simple, intuitive and
understandable.
Transformation-based learning has also been
applied to sentence parsing.
April 2005
CLINT Lecture IV
15
The Three Approaches
Compared



Rule Based
 Hand crafted rules
 It takes too long to come up with good rules
 Portability problems
Stochastic
 Find the sequence with the highest probability – Viterbi Algorithm
 Result of training not accessible to humans
 Large storage requirements for intermediate results whilst
training.
Transformation
 Rules are learned
 Small number of rules
 Rules can be inspected and modified by humans
April 2005
CLINT Lecture IV
16