Generation of Referring Expressions: Modeling Partner Effects

1
Generation of Referring Expressions Modeling
Partner Effects

• Surabhi Gupta
• Advisor Amanda Stent
• Department of Computer Science

2
Outline

• Introduction
• Data
• Previous work
• Modeling partner effects
• Generating NP postmodifiers
• A little statistical experiment
• Discussion and Future Work

3
Referring Expressions

• A referring expression denotes (or points to) an
  object in the world of a discourse.
• Examples of referring expressions include the red
  chair, the 400 dollar red chair and 5 red chairs.
  
• Referring expressions are usually noun phrases
• Improper construction of a referring expression
  can result in
• referring expressions that are ambiguous (e.g.
  the book when there are two books).
• referring expressions that are too descriptive
  and lead to false implicatures (e.g. the 400
  dollar chair when there is only one chair)

4
Structure of a Noun Phrase

• A definite/indefinite noun phrase is constructed
  of
• An (optional) determiner or quantifier e.g. a,
  three
• A number of premodifiers (adjectives, adverbs,
  noun modifiers) e.g. red
• A number of postmodifiers (prepositional phrases,
  relative clauses) e.g. worth 400 dollars, that is
  red
• Other noun phrases include pronouns, proper
  nouns, deictics

green
5
Adaptation in Conversation

• When people talk with each other, they adapt to
  the others choice of referring expression (Clark
  1996, Levinson 1983, Brennan 1987).
• Example
• (A) Lets buy the 400 dollar red chair
• (B) Thats a good idea. The chair matches with
  the red table.
• (A) The chair it is then.

6
Generation of Referring Expressions in Dialog

• When a computer constructs human language, it is
  called generation
• NewsBlaster summaries, or Google translation
• Generation for dialog must involve consideration
  of the dialog partner (the human)

7
Good Generation of Referring Expressions

• The algorithm should generate a referring
  expression for which the human reader can
  identify the referent.
• The algorithm should generate referring
  expressions that do not lead the human reader to
  make false implicatures (Grice 1968).
• The algorithm should model how conversational
  partners adapt to each other.
• The algorithm should be able to generate the
  whole range of referring expressions observed in
  discourse.
• The algorithm should be computationally feasible.

8
Our Objective

• We are building a model of referring expression
  generation that captures adaptation to partners
  in conversation.
• Related work in this field does not include
  partner adaptation for dialog (Dale and Reiter
  1995, Siddharthan and Copestake 2004).

9
Outline

• Introduction
• Data
• Previous work
• Modeling partner effects
• Generating NP postmodifiers
• A little statistical experiment
• Discussion and Future Work

10
Data

• Two corpora of spoken dialog rich in noun
  phrases
• Maptask - Speaker A giving instructions to
  Speaker B about following directions in a map
• Coconut - Two participants trying to buy
  furniture by using both of their inventories and
  money.
• For each corpus, we
• Automatically extracted the noun phrases
• Annotated the noun phrases by hand for referent
  (in a knowledge representation we built), type
  (noun phrase or pronoun), and to indicate whether
  the noun phrase was embedded in another noun
  phrase.

11
Coconut Maptask
Def 116 2118
Indef 967 1411
1st person pronoun 440 563
2nd person pronoun 165 1275
3rd person pronoun 79 614
Deictics 0 0
Proper Nouns 0 0
Quantity Nouns 291 160
Mass Nouns 0 0
No Modifiers 13 113
Not Embedded 229 1633
Embedded 242 26
Set Constructions 0 0
Not in KR 612 1875
NPs Used 471 1294
Total 1767 5986
12
Outline

• Introduction
• Data
• Previous work
• Modeling partner effects
• Generating NP postmodifiers
• A little statistical experiment
• Discussion and Future Work

13
Algorithms Compared

• Rule Based
• Dale and Reiter 1995
• With partner effects (x 2)
• With postmodifier ordering (x 4)
• Siddharthan and Copestake 2004
• With partner effects (x 2)
• With postmodifier ordering (x 4)
• Statistical
• Support Vector Machines

14
Rule-Based Algorithms

• Terms used
• Contrast Set contains information of all the
  objects in the world.
• Preferred list of attributes the attributes that
  are known for the objects.
• For Coconut type, quantity, cost, color, state
• E.g. three green high tables worth 400
• Intended Referent The object from the world,
  which we are trying to describe.

15
Dale and Reiter

• Basic idea
• Specify the preference list by hand
• Repeat until all members of the contrast set are
  gone
• Add the value for the next attribute from the
  preference list for the intended referent to the
  noun phrase to be generated

16
200 dollar green couch
300 dollar red couch
250 dollar brown table

• Example
• Preference list Type, Color, Cost, Quantity,
  State
• Contrast set 300 dollar red couch, 200 dollar
  green couch, 250 dollar brown table
• Intended referent 200 dollar green couch
• Generated NP green couch

17
Siddharthan and Copestake

• Basic idea See Dale and Reiter
• Preference list is reordered by using synonyms
  and antonyms of words in each attribute

18
Benefits to Rule Based Algorithms

• They consider the way humans actually converse
  ie. humans use unnecessary attributes, they also
  begin mentioning a referring expression without
  scanning the entire list of distractors.
• They do not attempt to look for the optimal
  number of attributes. They just go through the
  list of preferred attributes and iteratively
  includes those attributes that rule out at least
  one distractor from the contrast set.
• There is no backtracking and the head noun is
  always included.

19
Disadvantages to Rule Based Algorithms

• They dont generate the whole range of referring
  expressions
• Ones with postmodifiers
• Pronouns
• Deictics
• They dont model adaptation to partners.

20
Outline

• Introduction
• Data
• Previous work
• Modeling partner effects
• Generating NP postmodifiers
• A little statistical experiment
• Discussion and Future Work

21
Adding Partner Effects

• A rule based algorithm
• Basic idea See Dale and Reiter, Siddharthan and
  Copestake
• Preference list is reordered to match selection
  of attributes in previous mentions of the
  intended referent.
• Variant to this where those attributes mentioned
  previously are definitely included even if all
  the competitors have been eliminated.

22
Evaluation

• Metric Correct / Correct Inserted Deleted
  Moved
• Example
• Human the big fat green cat
• Computer the green happy cat
• Correct the, cat
• Inserted happy
• Deleted big, fat
• Moved green
• Score 2 / 6

23
Results

• The variant to our partner effects algorithms
  performs significantly better that our Baseline,
  Dale and Reiter and Siddharthan and Copestake for
  both the cropora used.

24
Outline

• Introduction
• Data
• Previous work
• Modeling partner effects
• Generating NP postmodifiers
• A little statistical experiment
• Discussion and Future Work

25
Discussion and Conclusions

• The corpus you choose makes a difference
• Maptask Few distractors, no significant
  different between Baseline, Dale and Reiter and
  Siddharthan and Copestake
• Do partner effects make a difference?

26
References

• Advaith Siddharthan and Ann Copestake. 2004.
  Generating Referring Expressions in Open Domains.
  In Proceedings of the 42th Meeting of the
  Association for Computational Linguistics Annual
  Conference (ACL 2004), Barcelona, Spain.
• Grice, H P (1975). Logic and conversation. In P.
  Cole and J. Morgan, editors, Syntax and
  Semantics Vol 3, Speech Acts, pages 43-58. New
  York Academic Press.
• Grosz, B and Sidner, C (1986). Attention,
  intention, and the structure of discourse.
  Computational Linguistics, 12 175-206.
• Robert Dale and Ehud Reiter. 1995. Computational
  interpretations of the Gricean maxims in the
  generation of referring expressions. Cognitive
  Science, 19233263.

27
Acknowledgements

• Dr. Amanda Stent, for all her time and efforts
  during the last three years.
• The Natural Language Processing Lab in Computer
  Science.
• The Honors College for giving me the chance of
  working on this year long project.
• NSF

28
Questions?
29
Outline

• Introduction
• Data
• Previous work
• Modeling partner effects
• Generating NP postmodifiers
• A little statistical experiment
• Discussion and Future Work

30
Generating with Postmodifiers

• Why? -- because previous algorithms dont but
  its a big part of the corpus we have used.
• Random - randomly decide whether the attribute
  selected should be a post modifier or premodifier
• Unigrams - see where the attribute is in relation
  to the type.
• Bigrams - statistics of pairs of attributes. E.g
  probability of finding an attribute given
  another.

31
Results
32
Outline

• Introduction
• Data
• Previous work
• Modeling partner effects
• Generating NP postmodifiers
• A little statistical experiment
• Discussion and Future Work

33
Support Vector Machines

• SVMs are a set of machine learning algorithms for
  binary classification that have been applied to
  NLP.
• We used a set of SVMs, one per attribute, that
  voted yes or no to use this attribute at this
  point in the noun phrase.
• Maptask 6 attributes, Coconut 5 attributes
• We evaluated using
• 10-fold cross-validation for Maptask.
• 4-fold cross-validation for Coconut.

34
Evaluation
35
Results