Transcript CS60057 Speech &Natural Language Processing Autumn 2007 Lecture 3 27 July 2007 Lecture 1, 7/21/2005 Natural Language Processing.

CS60057
Speech &Natural Language
Processing
Autumn 2007
Lecture 3
27 July 2007
Lecture 1, 7/21/2005
Natural Language Processing
1
Levels of (Formal) Description

6 basic levels (more or less explicitly present in most theories):
and beyond (pragmatics/logic/...)
meaning (semantics)
(surface) syntax
morphology
phonology
phonetics/orthography

Each level has an input and output representation
 output from one level is the input to the next (upper) level
 sometimes levels might be skipped (merged) or split
2
Phonetics/Orthography

Input:
 acoustic signal (phonetics) / text (orthography)

Output:
 phonetic alphabet (phonetics) / text (orthography)

Deals with:
 Phonetics:




consonant & vowel (& others) formation in the vocal tract
classification of consonants, vowels, ... in relation to
frequencies, shape & position of the tongue and various
muscles
intonation
Orthography: normalization, punctuation, etc.
3
Phonology

Input:
 sequence of phones/sounds (in a phonetic alphabet); or
“normalized” text (sequence of (surface) letters in one
language’s alphabet) [NB: phones vs. phonemes]

Output:
 sequence of phonemes (~ (lexical) letters; in an abstract
alphabet)

Deals with:
 relation between sounds and phonemes (units which might
have some function on the upper level)
 e.g.: [u] ~ oo (as in book), [æ] ~ a (cat); i ~ y (flies)
4
Morphology

Input:
 sequence of phonemes (~ (lexical) letters)

Output:
 sequence of pairs (lemma, (morphological) tag)

Deals with:
 composition of phonemes into word forms and their
underlying lemmas (lexical units) + morphological
categories (inflection, derivation, compounding)
 e.g. quotations ~ quote/V + -ation(der.V->N) + NNS.
5
(Surface) Syntax



Input:
 sequence of pairs (lemma, (morphological) tag)
Output:
 sentence structure (tree) with annotated nodes (all
lemmas, (morphosyntactic) tags, functions), of various
forms
Deals with:
 the relation between lemmas & morphological
categories and the sentence structure
 uses syntactic categories such as Subject, Verb,
Object,...


e.g.: I/PP1 see/VB a/DT dog/NN ~
6
((I/sg)SB ((see/pres)V (a/ind dog/sg)OBJ)VP)S
Meaning (semantics)



Input:
 sentence structure (tree) with annotated nodes
(lemmas, (morphosyntactic) tags, surface functions)
Output:
 sentence structure (tree) with annotated nodes
(semantic lemmas, (morpho-syntactic) tags, deep
functions)
Deals with:
 relation between categories such as “Subject”, “Object”
and (deep) categories such as “Agent”, “Effect”; adds
other cat’s
 e.g. ((I)SB ((was seen)V (by Tom)OBJ)VP)S ~
7

(I/Sg/Pat/t (see/Perf/Pred/t) Tom/Sg/Ag/f)
...and Beyond




Input:
 sentence structure (tree): annotated nodes (autosemantic
lemmas, (morphosyntactic) tags, deep functions)
Output:
 logical form, which can be evaluated (true/false)
Deals with:
 assignment of objects from the real world to the nodes of
the sentence structure
 e.g.: (I/Sg/Pat/t (see/Perf/Pred/t) Tom/Sg/Ag/f) ~
see(Mark-Twain[SSN:...],Tom-Sawyer[SSN:...])[Time:bef
99/9/27/14:15][Place:39ş19’40”N76ş37’10”W]
8
Three Views

Three equivalent formal ways to look at what we’re up to
(not including tables)
Regular Expressions
Finite State Automata
Lecture 1, 7/21/2005
Regular Languages
Natural Language Processing
9
Transition



Finite-state methods are particularly useful in dealing
with a lexicon.
Lots of devices, some with limited memory, need access
to big lists of words.
So we’ll switch to talking about some facts about words
and then come back to computational methods
Lecture 1, 7/21/2005
Natural Language Processing
10
MORPHOLOGY
Lecture 1, 7/21/2005
Natural Language Processing
11
Morphology


Morphology is the study of the ways that words are built up from
smaller meaningful units called morphemes
(morph = shape, logos = word)
We can usefully divide morphemes into two classes
 Stems: The core meaning bearing units
 Affixes: Bits and pieces that adhere to stems to change their
meanings and grammatical functions
 Prefix: un-, anti-, etc
 Suffix: -ity, -ation, etc
 Infix: are inserted inside the stem
 Tagalog: um + hingi humingi




Circumfixes – precede and follow the stem
English doesn’t stack more affixes.
But Turkish can have words with a lot of suffixes.
Languages, such as Turkish, tend to string affixes together are
called agglutinative languages.
Lecture 1, 7/21/2005
Natural Language Processing
12
Surface and Lexical Forms



The surface level of a word represents the actual spelling
of that word.
 geliyorum eats cats kitabım
The lexical level of a word represents a simple concatenation
of morphemes making up that word.
 gel +PROG +1SG
 eat +AOR
 cat +PLU
 kitap +P1SG
Morphological processors try to find correspondences between
lexical and surface forms of words.
 Morphological recognition/ analysis – surface to lexical
 Morphological generation/ synthesis – lexical to surface
Lecture 1, 7/21/2005
Natural Language Processing
13
Morphology: Morphemes & Order

Handles what is an isolated form in written text

Grouping of phonemes into morphemes
 sequence deliverables ~ deliver, able and
s (3 units)

Morpheme Combination
 certain combinations/sequencing possible, other not:


deliver+able+s, but not able+derive+s; noun+s, but not
noun+ing
typically fixed (in any given language)
14
Inflectional & Derivational Morphology
We can also divide morphology up into two broad classes
 Inflectional
 Derivational
 Inflectional morphology concerns the combination of stems and
affixes where the resulting word
 Has the same word class as the original
 Serves a grammatical/semantic purpose different from the
original
After a combination with an inflectional morpheme,
the meaning and class of the actual stem usually do not change.
 eat / eats
pencil / pencils
 After a combination with an derivational morpheme, the meaning
and the class of the actual stem usually change.
 compute / computer
do / undo
friend / friendly
 Uygar / uygarlaş
kapı / kapıcı
 The irregular changes may happen with derivational affixes.

Lecture 1, 7/21/2005
Natural Language Processing
15
Morphological Parsing


Morphological parsing is to find the lexical form of a word
from its surface form.
 cats -- cat +N +PLU
 cat -- cat +N +SG
 goose -- goose +N +SG or goose +V
 geese -- goose +N +PLU
 gooses -- goose +V +3SG
 catch -- catch +V
 caught -- catch +V +PAST or catch +V +PP
There can be more than one lexical level representation
for a given word. (ambiguity)
Lecture 1, 7/21/2005
Natural Language Processing
16
Morphological Analysis



Analyzing words into their linguistic components (morphemes).
Morphemes are the smallest meaningful units of language.
cars
car+PLU
giving
give+PROG
AsachhilAma AsA+PROG+PAST+1st I/We was/were coming
Ambiguity: More than one alternatives
flies
flyVERB+PROG
flyNOUN+PLU
mAtAla
kare
Lecture 1, 7/21/2005
Natural Language Processing
17


Fly + s  flys  flies (y i rule)
Duckling
Go-getter  get + er
Doer  do + er
Beer  ?
What knowledge do we need?
How do we represent it?
How do we compute with it?
Lecture 1, 7/21/2005
Natural Language Processing
18
Knowledge needed



Knowledge of stems or roots
 Duck is a possible root, not duckl
We need a dictionary (lexicon)
Only some endings go on some words
 Do + er ok
 Be + er – not ok
In addition, spelling change rules that adjust the surface
form
 Get + er – double the t getter
 Fox + s – insert e – foxes
 Fly + s – insert e – flys – y to i – flies
 Chase + ed – drop e - chased
Lecture 1, 7/21/2005
Natural Language Processing
19
Put all this in a big dictionary (lexicon)




Turkish – approx 600  106 forms
Finnish – 107
Hindi, Bengali, Telugu, Tamil?
Besides, always novel forms can be constructed
 Anti-missile


Anti-anti-missile
 Anti-anti-anti-missile
 ……..
Compounding of words – Sanskrit, German
Lecture 1, 7/21/2005
Natural Language Processing
20
Morphology: From Morphemes to
Lemmas & Categories

Lemma: lexical unit, “pointer” to lexicon
 typically is represented as the “base form”, or
“dictionary headword”



possibly indexed when ambiguous/polysemous:
 state1 (verb), state2 (state-of-the-art), state3 (government)
from one or more morphemes (“root”, “stem”,
“root+derivation”, ...)
Categories: non-lexical
 small number of possible values (< 100, often < 5-10)
21
Morphology Level: The Mapping

Formally: A+  2(L,C1,C2,...,Cn)
 A is the alphabet of phonemes (A+ denotes any non-empty
sequence of phonemes)
 L is the set of possible lemmas, uniquely identified
 Ci are morphological categories, such as:





grammatical number, gender, case
person, tense, negation, degree of comparison, voice, aspect,
...
tone, politeness, ...
part of speech (not quite morphological category, but...)
A, L and Ci are obviously language-dependent
22
Morphological Analysis (cont.)


Relatively simple for English.
But for many Indian languages, it may be more difficult.
Examples
Inflectional and Derivational Morphology.
 Common tools: Finite-state transducers
Lecture 1, 7/21/2005
Natural Language Processing
23
Bengali Verb Paradigms
Lecture 1, 7/21/2005
Natural Language Processing
24
Bengali Verb morphology for one of the
paradigms
Lecture 1, 7/21/2005
Natural Language Processing
25
Lecture 1, 7/21/2005
Natural Language Processing
26
Lecture 1, 7/21/2005
Natural Language Processing
27
Finite State Machines




FSAs are equivalent to regular languages
FSTs are equivalent to regular relations (over pairs of
regular languages)
FSTs are like FSAs but with complex labels.
We can use FSTs to transduce between surface and
lexical levels.
Lecture 1, 7/21/2005
Natural Language Processing
28
Simple Rules
Lecture 1, 7/21/2005
Natural Language Processing
29
Adding in the Words
Lecture 1, 7/21/2005
Natural Language Processing
30
Derivational Rules
Lecture 1, 7/21/2005
Natural Language Processing
31
Parsing/Generation
vs. Recognition


Recognition is usually not quite what we need.
 Usually if we find some string in the language we need
to find the structure in it (parsing)
 Or we have some structure and we want to produce a
surface form (production/generation)
Example
 From “cats” to “cat +N +PL” and back
Lecture 1, 7/21/2005
Natural Language Processing
32
Morphological Parsing


Given the input cats, we’d like to output
cat +N +Pl,
telling us that cat is a plural noun.
Given the Spanish input bebo, we’d like to output
beber +V +PInd +1P +Sg
telling us that bebo is the present indicative first person singular
form of the Spanish verb beber, ‘to drink’.
Lecture 1, 7/21/2005
Natural Language Processing
33
Morphological Anlayser
To build a morphological analyser we need:
 lexicon: the list of stems and affixes, together with basic information
about them
 morphotactics: the model of morpheme ordering (eg English plural
morpheme follows the noun rather than a verb)
 orthographic rules: these spelling rules are used to model the
changes that occur in a word, usually when two morphemes
combine (e.g., fly+s = flies)
Lecture 1, 7/21/2005
Natural Language Processing
34
Lexicon & Morphotactics



Typically list of word parts (lexicon) and the models of
ordering can be combined together into an FSA which
will recognise the all the valid word forms.
For this to be possible the word parts must first be
classified into sublexicons.
The FSA defines the morphotactics (ordering
constraints).
Lecture 1, 7/21/2005
Natural Language Processing
35
Sublexicons
to classify the list of word parts
reg-noun
irreg-pl-noun
irreg-sg-noun
plural
cat
mice
mouse
-s
fox
sheep
sheep
geese
goose
Lecture 1, 7/21/2005
Natural Language Processing
36
FSA Expresses Morphotactics
(ordering model)
Lecture 1, 7/21/2005
Natural Language Processing
37
Towards the Analyser


We can use lexc or xfst to build such an FSA (see
lex1.lexc)
To augment this to produce an analysis we must create a
transducer Tnum which maps between the lexical level
and an "intermediate" level that is needed to handle the
spelling rules of English.
Lecture 1, 7/21/2005
Natural Language Processing
38
Three Levels of Analysis
Lecture 1, 7/21/2005
Natural Language Processing
39
1. Tnum: Noun Number Inflection
• multi-character symbols
• morpheme boundary ^
• word boundary #
Lecture 1, 7/21/2005
Natural Language Processing
40
Intermediate Form to Surface


The reason we need to have an intermediate form is that
funny things happen at morpheme boundaries, e.g.
cat^s  cats
fox^s  foxes
fly^s  flies
The rules which describe these changes are called
orthographic rules or "spelling rules".
Lecture 1, 7/21/2005
Natural Language Processing
41
More English Spelling Rules






consonant doubling: beg / begging
y replacement: try/tries
k insertion: panic/panicked
e deletion: make/making
e insertion: watch/watches
Each rule can be stated in more detail ...
Lecture 1, 7/21/2005
Natural Language Processing
42
Spelling Rules


Chomsky & Halle (1968) invented a special notation for
spelling rules.
A very similar notation is embodied in the "conditional
replacement" rules of xfst.
E -> F || L _ R
which means replace E with F when it appears between
left context L and right context R
Lecture 1, 7/21/2005
Natural Language Processing
43
A Particular Spelling Rule
This rule does e-insertion
^ -> e || x _ s#
Lecture 1, 7/21/2005
Natural Language Processing
44
e insertion over 3 levels
The rule corresponds to the mapping between
surface and intermediate levels
Lecture 1, 7/21/2005
Natural Language Processing
45
e insertion as an FST
Lecture 1, 7/21/2005
Natural Language Processing
46
Incorporating Spelling Rules



Spelling rules, each corresponding to an FST, can be run in parallel
provided that they are "aligned".
The set of spelling rules is positioned between the surface level and
the intermediate level.
Parallel execution of FSTs can be carried out:
 by simulation: in this case FSTs must first be aligned.
 by first constructing a a single FST corresponding to their
intersection.
Lecture 1, 7/21/2005
Natural Language Processing
47
Putting it all together
execution of FSTi
takes place in
parallel
Lecture 1, 7/21/2005
Natural Language Processing
48
Kaplan and Kay
The Xerox View
FSTi are aligned
but separate
Lecture 1, 7/21/2005
FSTi intersected
together
Natural Language Processing
49
Finite State Transducers

The simple story
 Add another tape
 Add extra symbols to the transitions

On one tape we read “cats”, on the other we write
“cat +N +PL”, or the other way around.
Lecture 1, 7/21/2005
Natural Language Processing
50
FSTs
Lecture 1, 7/21/2005
Natural Language Processing
51
English Plural
surface
lexical
cat
cat+N+Sg
cats
cat+N+Pl
foxes
fox+N+Pl
mice
mouse+N+Pl
sheep
sheep+N+Pl
sheep+N+Sg
Lecture 1, 7/21/2005
Natural Language Processing
52
Transitions
c:c



a:a
t:t
+N:ε
+PL:s
c:c means read a c on one tape and write a c on the other
+N:ε means read a +N symbol on one tape and write nothing on the
other
+PL:s means read +PL and write an s
Lecture 1, 7/21/2005
Natural Language Processing
53
Typical Uses


Typically, we’ll read from one tape using the first symbol
on the machine transitions (just as in a simple FSA).
And we’ll write to the second tape using the other
symbols on the transitions.
Lecture 1, 7/21/2005
Natural Language Processing
54
Ambiguity


Recall that in non-deterministic recognition multiple
paths through a machine may lead to an accept state.
 Didn’t matter which path was actually traversed
In FSTs the path to an accept state does matter since
differ paths represent different parses and different
outputs will result
Lecture 1, 7/21/2005
Natural Language Processing
55
Ambiguity


What’s the right parse for
 Unionizable
 Union-ize-able
 Un-ion-ize-able
Each represents a valid path through the derivational
morphology machine.
Lecture 1, 7/21/2005
Natural Language Processing
56
Ambiguity

There are a number of ways to deal with this problem
 Simply take the first output found
 Find all the possible outputs (all paths) and return
them all (without choosing)
 Bias the search so that only one or a few likely paths
are explored
Lecture 1, 7/21/2005
Natural Language Processing
57
The Gory Details



Of course, its not as easy as
 “cat +N +PL” <->
“cats”
As we saw earlier there are geese, mice and oxen
But there are also a whole host of spelling/pronunciation
changes that go along with inflectional changes
 Cats vs Dogs
 Fox and Foxes
Lecture 1, 7/21/2005
Natural Language Processing
58
Multi-Tape Machines


To deal with this we can simply add more tapes and use
the output of one tape machine as the input to the next
So to handle irregular spelling changes we’ll add
intermediate tapes with intermediate symbols
Lecture 1, 7/21/2005
Natural Language Processing
59
Generativity



Nothing really privileged about the directions.
We can write from one and read from the other or viceversa.
One way is generation, the other way is analysis
Lecture 1, 7/21/2005
Natural Language Processing
60
Multi-Level Tape Machines

We use one machine to transduce between the lexical and the
intermediate level, and another to handle the spelling changes to the
surface tape
Lecture 1, 7/21/2005
Natural Language Processing
61
Lexical to Intermediate Level
Lecture 1, 7/21/2005
Natural Language Processing
62
Intermediate to Surface

The add an “e” rule as in fox^s# <-> foxes#
Lecture 1, 7/21/2005
Natural Language Processing
63
Foxes
Lecture 1, 7/21/2005
Natural Language Processing
64
Note



A key feature of this machine is that it doesn’t do
anything to inputs to which it doesn’t apply.
Meaning that they are written out unchanged to the
output tape.
Turns out the multiple tapes aren’t really needed; they
can be compiled away.
Lecture 1, 7/21/2005
Natural Language Processing
65
Overall Scheme


We now have one FST that has explicit information
about the lexicon (actual words, their spelling, facts
about word classes and regularity).
 Lexical level to intermediate forms
We have a larger set of machines that capture
orthographic/spelling rules.
 Intermediate forms to surface forms
Lecture 1, 7/21/2005
Natural Language Processing
66
Overall Scheme
Lecture 1, 7/21/2005
Natural Language Processing
67