Reference Resolution

1
Reference Resolution

• CMSC 35900-1
• Discourse and Dialogue
• October 12, 2004

2
Agenda

• Coherence Holding discourse together
• Coherence types and relations
• Reference resolution
• Knowledge-rich, deep analysis approaches
• LappinLeass, Centering, Hobbs
• Knowledge-based, shallow analysis CogNIAC (95)
• Learning approaches
• Fully, Weakly Supervised
• CardieNg 02,03,04

3
Data-driven Reference Resolution

• Prior approaches
• Knowledge-based, hand-crafted
• Data-driven machine learning approach
• Cast coreference as classification problem
• For each pair NPi,NPj, do they corefer?
• Cluster to form equivalence classes

4
NP Coreference Examples

• Link all NPs that refer to same entity

Queen Elizabeth set about transforming her
husband, King George VI, into a viable monarch.
Logue, a renowned speech therapist, was summoned
to help the King overcome his speech
impediment...
5
Training Instances

• 25 features per instance 2NPs, features, class
• lexical (3)
• string matching for pronouns, proper names,
  common nouns
• grammatical (18)
• pronoun_1, pronoun_2, demonstrative_2,
  indefinite_2,
• number, gender, animacy
• appositive, predicate nominative
• binding constraints, simple contra-indexing
  constraints,
• span, maximalnp,
• semantic (2)
• same WordNet class
• alias
• positional (1)
• distance between the NPs in terms of of
  sentences
• knowledge-based (1)
• naïve pronoun resolution algorithm

6
Classification Clustering

• Classifiers
• C4.5 (Decision Trees), RIPPER
• Cluster Best-first, single link clustering
• Each NP in own class
• Test preceding NPs
• Select highest confidence coref, merge classes
• Tune Training sample skew class, type

7
Classifier for MUC-6 Data Set
8
Problem 1

• Coreference is a rare relation
• skewed class distributions (2 positive
  instances)
• remove some negative instances

NP3
NP4
NP5
NP6
NP7
NP8
NP9
NP2
NP1
farthest antecedent
9
Problem 2

• Coreference is a discourse-level problem
• different solutions for different types of NPs
• proper names string matching and aliasing
• inclusion of hard positive training instances
• positive example selection selects easy positive
  training instances (cf. Harabagiu et al. (2001))

Queen Elizabeth set about transforming her
husband, King George VI, into a viable monarch.
Logue, the renowned speech therapist, was
summoned to help the King overcome his speech
impediment...
10
Problem 3

• Coreference is an equivalence relation
• loss of transitivity
• need to tighten the connection between
  classification and clustering
• prune learned rules w.r.t. the clustering-level
  coreference scoring function

coref ?
coref ?
Queen Elizabeth set about transforming her
husband, ...
not coref ?
11
Weakly Supervised Learning

• Exploit small pool of labeled training data
• Larger pool unlabeled
• Single-View Multi-Learner Co-training
• 2 different learning algorithms, same feature set
• each classifier labels unlabeled instances for
  the other classifier
• data pool is flushed after each iteration

12
Effectiveness

• Supervised learning approaches
• Comparable performance to knowledge-based
• Weakly supervised approaches
• Decent effectiveness, still lags supervised
• Dramatically less labeled training data
• 1K vs 500K

13
Reference Resolution Extensions

• Cross-document co-reference
• (Baldwin Bagga 1998)
• Break the document boundary
• Question John Smith in A John Smith in B?
• Approach
• Integrate
• Within-document co-reference
• with
• Vector Space Model similarity

14
Cross-document Co-reference

• Run within-document co-reference (CAMP)
• Produce chains of all terms used to refer to
  entity
• Extract all sentences with reference to entity
• Pseudo per-entity summary for each document
• Use Vector Space Model (VSM) distance to compute
  similarity between summaries

15
Cross-document Co-reference

• Experiments
• 197 NYT articles referring to John Smith
• 35 different people, 24 1 article each
• With CAMP Precision 92 Recall 78
• Without CAMP Precision 90 Recall 76
• Pure Named Entity Precision 23 Recall 100

16
Conclusions

• Co-reference establishes coherence
• Reference resolution depends on coherence
• Variety of approaches
• Syntactic constraints, Recency, Frequency,Role
• Similar effectiveness - different requirements
• Co-reference can enable summarization within and
  across documents (and languages!)

17
Challenges

• Alternative approaches to reference resolution
• Different constraints, rankings, combination
• Different types of referent
• Speech acts, propositions, actions, events
• Inferrables - e.g. car -gt door, hood, trunk,..
• Discontinuous sets
• Generics
• Time

18
Discourse Structure Theories

• Discourse Dialogue
• CMSC 35900-1
• October 12, 2004

19
Roadmap

• Goals of Discourse Structure Models
• Limitations of early approaches
• Models of Discourse Structure
• Attention Intentions (Grosz Sidner 86)
• Rhetorical Structure Theory (Mann Thompson 87)
• Contrasts, Constraints Conclusions

20
Why Model Discourse Structure?(Theoretical)

• Discourse not just constituent utterances
• Create joint meaning
• Context guides interpretation of constituents
• How????
• What are the units?
• How do they combine to establish meaning?
• How can we derive structure from surface forms?
• What makes discourse coherent vs not?
• How do they influence reference resolution?

21
Why Model Discourse Structure?(Applied)

• Design better summarization, understanding
• Improve speech synthesis
• Influenced by structure
• Develop approach for generation of discourse
• Design dialogue agents for task interaction
• Guide reference resolution

22
Early Discourse Models

• Schemas Plans
• (McKeown, Reichman, Litman Allen)
• Task/Situation model discourse model
• Specific-gtGeneral restaurant -gt AI planning
• Topic/Focus Theories (Grosz 76, Sidner 76)
• Reference structure discourse structure
• Speech Act
• single utt intentions vs extended discourse

23
Discourse Models Common Features

• Hierarchical, Sequential structure applied to
  subunits
• Discourse segments
• Need to detect, interpret
• Referring expressions provide coherence
• Explain and link
• Meaning of discourse more than that of component
  utterances
• Meaning of units depends on context

24
Earlier Models

• Issues
• Conflate different aspects of discourse
• Task plan, discourse plan
• Ignore aspects of discourse
• Goals intentions vs focus
• Overspecific
• Fixed plan, schema, relation inventory

25
Attention, Intentions and the Structure of
Discourse

• GroszSidner (1986)
• Goals
• Integrate approaches for focus (reference res.),
  plan/task structure, discourse structure, goals
• Three part model
• Linguistic structure (utterances)
• Attentional structure (focus, reference)
• Intentional structure (plans, purposes)

26
Linguistic Structure

• Utterances group into discourse segments
• Hierarchical, not ne, cessarily contiguous
• Not strictly decompositional
• 2-way interactions
• Utterances define structure
• Cue phrases mark segment boundaries
• But, okay, fine, incidentally
• Structure guides interpretation
• Reference

27
Intentional Structure

• Discourse participants overall purpose
• Discourse segments have purposes (DP/DSP)
• Contribute to overall
• Main DP/DSP intended to be recognized

28
Intentional Structure Relations

• Two relations between purposes
• Dominance
• DSP1 dominates DSP2 if doing DSP2 contributes to
  achieving DSP1
• Satisfaction-Precedence
• DSP1 must be satisfied before DSP2
• Purposes
• Intend that someone know something, do something,
  believe something, etc
• Open-ended

29
Attentional State

• Captures focus of attention in discourse
• Incremental
• Focus Spaces
• Include entities salient/evoked in discourse
• Include a current DSP
• Stack-structured
• higher-gtmore salient, lower still accessible
• Pushsegment contributes to previous DSP
• Pop segment to contributes to more dominant DSP
• Tied to intentional structure

30
Attentional State cntd.

• Focusing structure depends on the intentional
  structure the relationships between DSPs
  determine pushes and pops from the stack
• Focusing structure coordinates the linguistic and
  intentional structures during processing
• Like the other 2 structures, focusing structure
  evolves as discourse proceeds

31
Discourse examples

• Essay
• Task-oriented dialog
• Intentional structure is neither identical nor
  isomorphic to the general plan

32
0
The "movies" are so attractive to the great
American public, especially to young people, that
it is time to take careful thought about their
effect on mind and morals. Ought any parent to
permit his children to attend a moving picture
show often or without being quite certain of the
show he permits them to see? No one can deny, of
course, that great educational and ethical gains
may be made through the movies because of their
astonishing vividness. But the important fact to
be determined is the total result of continuous
and indiscriminate attendance on shows of this
kind. Can it other than harmful? In the first
place the character of the plays is seldom of the
best. One has only to read the ever-present
"movie" billboard to see how cheap, melodramatic
and vulgar most of the photoplays are. Even the
best plays, moreover, are bound to be exciting
and over-emotional. Without spoken words, facial
expression and gesture must carry the meaning
but only strong emotion or buffoonery can be
represented through facial expression and
gesture. The more reasonable and quiet aspects of
life are necessarily neglected. How can our young
people drink in through their eyes a continuous
spectacle of intense and strained activity and
feeling without harmful effects? Parents and
teachers will do well to guard the young against
overindulgence in the taste for the "movie".
1
2
3
4
5
6
33
H1. First you have to remove the flywheel . R2.
How do I remove the flywheel? H3. First, loosen
the screw , then pull it off. R4. OK .5. The
tool I have is awkward. Is there another tool
that I could use instead? H6. Show me the tool
you are using. R7. OK. H8. Are you sure you are
using the right size key? R9. Ill try some
others. 10. I found an angle I can get at it
. 11. The screw is loose, but Im having trouble
getting the flywheel off. H12. Use the
wheelpuller . Do you know how to use it ? R13.
No. H14. Do you know what it looks like? R15.
Yes. H16. Show it to me please. R17. OK. H18.
Good. Loosen the screw in the center and place
the jaws around the hub of the flywheel, then
tighten the screw onto the center of the shaft.
The flywheel should slide off.
34
Processing issues

• Intention recognition
• What info can be used to recognize an intention
• At what point does this info become available
• Overall processing module has to be able to
  operate on partial information
• It must allow for incrementally constraining the
  range of possibilities on the basis of new info
  that becomes available as the segment progresses

35

• Info constraining DSP
• Specific linguistic markers
• Utterance-level intentions
• General knowledge about actions and objects in
  the domain of discourse
• Applications of the theory
• Interruptions
• Weak not linked to immediate DSP
• Strong - not linked to any DSP
• Cue words

36
Interruption

• John came by and left the groceries
• Stop that you kids
• And I put them away after he left

kids DSP2
John, groceries DSP1
John, groceries DSP1
37
Conclusions

• Generalizes approaches to task-oriented dialogue
• Goal Domain-independence
• Broad, general, abstract model
• Accounts for interesting phenomena
• Interruptions, returns, cue phrases

38
More conclusions

• Asks more questions than it answers.
• How do we implement these aspects of dialog?
• Is it remotely feasible????