Machine Learning for (Psycho-)Linguistics

1
Machine Learning for (Psycho-)Linguistics

• Walter Daelemans
• daelem_at_uia.ua.ac.be
• http//cnts.uia.ac.be
• CNTS, University of Antwerp
• ILK, Tilburg University
• QITL-02

2
Outline

• Machine Learning of Language
• Induction of rules and classes
• Learning by Analogy
• Case Studies
• Discovery of phonological categories and
  morphological rules
• A single-route model of morphological processing
• Issues
• Probabilities versus symbolic structure induction
• Nativism versus empiricism
• Exemplar analogy versus rules

3
Experience
BIAS
Learning Component
Search
Rj
Ri
Rk
Output
Input
Rl
Performance Component
4
Problems with Probabilities

• Explanation
• Also applies to neural networks
• Event relevance
• Especially in unsupervised learning (clustering)
• Incorporation of linguistic knowledge
• Smoothing zero-frequency events

5
(symbolic) machine learning

• Rule induction (understandable induced theories)
• Inductive Logic Programming (incorporating
  linguistic knowledge)
• Memory-based learning (similarity-based smoothing
  of sparse data, feature weighting)

6
Common Fallacies

• Rules nativism
• (and connections empiricism)
• Generalization abstraction
• (and memory table-lookup)

7
Rule-Based ? Innate

• Rules can be induced from primary linguistic data
  as well
• Applications in Linguistics
• Evaluation and comparison of linguistic
  hypotheses
• Discovery of linguistic generalizations and
  categories

8
Allomorphy in Dutch Diminutive

• one of the more spectacular phenomena of modern
  Dutch morphophonemics Trommelen (1983)
• Base form of Noun tje (5 variants)
• Linguistic theory (from Te Winkel 1862)
• Rime last syllable, stress, morphological
  structure,
• Trommelen 1983
• Local phenomenon, stress morphological
  structure do not play a role
• CELEX data (3900 nouns)
• - b i - z _at_ m A nt ? je

9
Allomorphs
10
Decision Tree Learning

• Given a data set, construct a decision tree that
  reflects the structure of the domain
• A decision tree is a tree where
• non-leaf nodes represent features (tests)
• branches leading out of a test represent possible
  values for the feature
• leaf nodes represent outcomes (classes)
• Decision Tree can be translated into a set of
  IF-THEN rules (with further optimization)
• Value grouping

11
Decision Tree Construction

• Given a set of examples T
• If T contains one or more cases all belonging to
  the same class C, then the decision tree for T is
  a leaf node with category C.
• If T contains different classes then
• Choose a feature, and partition T into subsets
  that have the same value for the feature chosen.
  The decision tree consists of a node containing
  the feature name, and a branch for each value
  leading to a subset.
• Apply the procedure recursively to subsets
  created this way.

12
Induced rule set

• Default class is -tje
• IF coda last is /lm/ or /rm/ THEN -pje
• IF nucleus last is bimoraic AND coda last is
  /m/ THEN -pje
• IF coda last is /N/ THEN
• IF nucleus penultimate is empty or schwa THEN
  -etje ELSE -kje
• IF nucleus last is short and coda last is
  nas or liq THEN -etje
• IF coda last is obstruent THEN -je

13
Results

• Problem is almost perfectly learnable (98.4)
• More than last syllable is needed for a full
  solution
• Only rime of last syllable (not stress or onset)
  is relevant
• Induced Categories
• Nasals, liquids, obstruents, short vowels,
  bimoraic vowels (consists of vowels, diphtongs,
  schwa)
• Task-dependent categories? Category formation is
  dependent on the task to be learned, not
  absolute, not language-independent

14
Conclusions Rule Induction in Linguistics

• Falsify existing linguistic theories
• Evaluate role of linguistic information sources
• (Re)discover interesting linguistic rules (
  supervised learning)
• (Re)discover interesting linguistic categories (
  unsupervised learning)
• Empiricist alternative for (mostly nativist)
  rule-based systems

15
There is one small problem

• Current methodology for comparative machine
  learning experiments is not reliable (especially
  with small data)
• Different runs of the algorithm provide different
  resulting rule sets
• Algorithm can be tweaked to get high performance
  with any information source combination
• Algorithm is highly sensitive to training data,
  feature selection, algorithm parameter settings,
  
• Only to be used as a heuristic
• As with your own rule induction module

16
Word Sense Disambiguation (do) Similar
experience, material, say, then,
keywords
Local Context
47.9
49.0
Default
59.5
60.8
Optimized parameters LC
61.0
Optimized parameters
60.8
17
Generalisation ? Abstraction
Rule Induction Connectionism Inductive Logic
Programming Statistics Handcrafting
abstraction
(Fill in your most hated linguist here)
generalisation
- generalisation
Memory-Based Learning
Table Lookup
- abstraction
18
MBL Use memory traces of experiences as a basis
for analogical reasoning, rather than using rules
or other abstractions extracted from experience
and replacing the experiences.
This rule of nearest neighbor has considerable
elementary intuitive appeal and probably
corresponds to practice in many situations. For
example, it is possible that much medical
diagnosis is influenced by the doctor's
recollection of the subsequent history of an
earlier patient whose symptoms resemble in some
way those of the current patient. (Fix and
Hodges, 1952, p.43)
19
-etje
Rule Induction
-kje
Coda last syl
Nucleus last syl
20
-etje
MBL
-kje
Coda last syl
?
Nucleus last syl
21
Memory-Based Learning

• Basis k nearest neighbor algorithm
• store all examples in memory
• to classify a new instance X, look up the k
  examples in memory with the smallest distance
  D(X,Y) to X
• let each nearest neighbor vote with its class
• classify instance X with the class that has the
  most votes in the nearest neighbor set
• Choices
• similarity metric
• number of nearest neighbors (k)
• voting weights

22
Metrics
ib1
ib1-ig
ib1-mvdm
23
Metrics (2)

• Voting options
• Equal weight for each nearest neighbor
• Distance weighted voting
• Inverse distance 1/D(X,Y) (Wettschereck, 1994)
• RBF-style gaussian voting function (Shepard,
  1987)
• Linear voting function (Dudani, 1976)

(NB weighted NN distribution can be used as
conditional probability)
24
MBL Acquisition

• Inflectional process is represented by a set of
  exemplars in memory
• Exemplars act as models
• Learning is incremental storage of exemplars
• Compression and Metrics
• Exemplar consists of set of (mostly symbolic)
  features

25
MBL Processing

• New instances of a performance process are solved
  through
• Memory-lookup
• Analogical (Similarity-Based) Reasoning
• Similarity metric
• Language (faculty) - independent
• Adaptive (feature and exemplar weighting)

26
The properties of language processing tasks

• Language processing tasks are mappings between
  linguistic representation levels that are
• context-sensitive (but mostly local!)
• complex (sub/ir/regularity), pockets of
  exceptions
• Similar representations at one linguistic level
  correspond to similar representations at the
  other level
• Several information sources interact in (often)
  unpredictable ways at the same level
• Data is sparse

27
fit the bias of MBL

• Inference is based on Similarity-Based /
  Analogical Reasoning
• Adaptive data fusion / relevance assignment is
  available through feature weighting
• It is a non-parametric approach
• Similarity-based smoothing is implicit
• Regularities and subregularities / exceptions can
  be modeled uniformly

28
German and Dutch plurals
29
Data Representation

• Symbolic features
• segmental information (syllable structure)
• stress
• gender
• German Plural ( 25,000 from CELEX)
• Vorlesung (lecture) l e - z U N F en
• Classes e (e)n s er - U- Uer Ue
• Dutch Plural ( 62,000 from CELEX)
• ontruiming (evacuation) 0 - O nt 1 r L - 0 m I N
  en
• Classes (e)n s (-eren, -i, -a, )

30
Cognitive Architectures of Inflectional Morphology
Dual Route

• Dual Route (Pinker, Clahsen, Marcus )
• Rules for regular cases
• (over)generalization
• default behaviour
• Associative memory for exceptions
• irregularization / family effects
• Single Route (RM, MacWhinney, Plunkett, Elman,
  )
• Frequency-based regularity

Suffix-class
Memory
Failure
Pattern
Rule
Associator
Input Features
31
German Plural

• Notoriously complex but routinely acquired (at
  age 5)
• Evidence for Dual Route ?
• -s suffix is default/regular (novel words,
  surnames, acronyms, )
• -s suffix is infrequent (least frequent of the
  five most important suffixes)

32
(No Transcript)
33
The default status of -s

• Similar item missing Fnöhk-s
• Surname, product name Mann-s
• Borrowings Kiosk-s
• Acronyms BMW-s
• Lexicalized phrases Vergissmeinnicht-s
• Onomatopoeia, truncated roots, derived nouns, ...

34
(No Transcript)
35
Discussion

• Three classes of plurals ((-en -)(-e -er))(s)
• the former 4 suffixes seem regular, can be
  accurately learned using information from
  phonology and gender
• -s is learned reasonably well but information is
  lacking
• Hypothesis more features are needed
  (syntactic, semantic, meta-linguistic, ) to
  enrich the lexical similarity space
• No difference in accuracy and speed of learning
  with and without Umlaut
• Overall generalization accuracy very high 95
• Schema-based learning (Köpcke).

,,,,i,r,M e
36
(No Transcript)
37
(No Transcript)
38
Acquisition DataSummary of previous studies

• Existing nouns
• (Park 78 Veit 86 Mills 86 Schamer-Wolles 88
  Clahsen et al. 93 Sedlak et al. 98)
• Children mainly overapply -e or -(e)n
• -s plurals are learned late
• Novel words
• (Mugdan 77 MacWhinney 78 Phillis Bouma 80
  Schöler Kany 89)
• Children inflect novel words with -e or -(e)n
• More irregular plural forms produced than
  defaults

39
MBL simulation

• model overapplies mainly -en and -e
• -s is learned late and imperfectly
• Mainly but not completely parallel to input
  frequency (more -s overgeneralization than -er
  generalization)

40
Bartke, Marcus, Clahsen (1995)

• 37 children age 3.6 to 6.6
• pictures of imaginary things, presented as
  neologisms
• names or roots
• rhymes of existing words or not
• choice -en or -s
• results
• children are aware that unusual sounding words
  require the default
• children are aware that names require the default

41
MBL simulation

• sort CELEX data according to rhyme
• compare overgeneralization
• to -en versus to -s
• percentage of total number of errors
• results
• when new words dont rhyme more errors are made
• overgeneralization to -en drops below the level
  of overgeneralization to -s

42
Dutch Plural

• Suffixes -en and -s are both defaults, and are in
  complementary distribution
• Selection of -en or -s governed by
• phonological structure of the base noun (stressed
  vs. unstressed last syllable)
• morphological structure (suffix of the base noun)
• loan word status
• semantic feature person vs. thing
• both are possible after /?/
• (Baayen et al. 2001)

43
Feature Relevance
44
Accuracy on CELEX

• Methodology
• Leave-one-out
• Results
• MBL 94.9 accuracy
• Prec Rec F?
• -(e)n 95.8 97.2 96.4
• -s 93.8 91.4 92.6
• -i 82.0 77.2 79.5
• without stress 94.9 accuracy
• last syllable with stress 92.6 accuracy
• last syllable without stress 92.4 accuracy
• rhyme last syllable 89.6 accuracy

45
Accuracy on pseudo-words

• Methodology
• Train Celex (all) and Celex (1000 most frequent
  types)
• Test 8 10 pseudo-words (Baayen et al., 2001)
• dreip - workel - bastus - bestroeting - kloertje
• stape - stree - kadisme
• Results accuracy number of decisions equal to
  subject majority for each item
• Subjects 87.5
• MBL (all) 83.8
• MBL (top 1000) 90.0

46
muidus, muidi nn modus, modi
Low frequency and loan word nearest neighbours
Celex bias
47
Conclusions Memory-Based Single Route

• MBLP picks up the main schemata of Dutch and
  German plural formation and their exceptions
  without recourse to explicit rules or a dual
  route architecture
• MBLP trained on (part of) CELEX matches subject
  behavior on pseudo words and acquisition data
• Segmental information suffices to reliably
  predict plural in Dutch and most plurals in
  German, additional information needed for German
  -s
• Heterogeneity and density in lexical exemplar
  space as source of behavior predictions

48
Overall Conclusions

• Advantages of symbolic machine learning methods
  over pure statistics
• As a methodology for inducing interpretable
  linguistic generalizations and categories
• As a way of introducing an operationalisation of
  analogy-based methods into (psycho)linguistics