conceptual coherence in the generation of referring expressions - PowerPoint PPT Presentation

Loading...

PPT – conceptual coherence in the generation of referring expressions PowerPoint presentation | free to download - id: 76e94e-YmRjN



Loading


The Adobe Flash plugin is needed to view this content

Get the plugin now

View by Category
About This Presentation
Title:

conceptual coherence in the generation of referring expressions

Description:

conceptual coherence in the generation of referring expressions Albert Gatt & Kees van Deemter University of Aberdeen {agatt, kvdeemte}_at_csd.abdn.ac.uk – PowerPoint PPT presentation

Number of Views:28
Avg rating:3.0/5.0
Slides: 30
Provided by: agatt
Learn more at: http://homepages.abdn.ac.uk
Category:

less

Write a Comment
User Comments (0)
Transcript and Presenter's Notes

Title: conceptual coherence in the generation of referring expressions


1
conceptual coherence in the generation of
referring expressions
  • Albert Gatt Kees van Deemter
  • University of Aberdeen
  • agatt, kvdeemte_at_csd.abdn.ac.uk

2
  • Gatt and Van Deemter 2007 Lexical Choice and
    conceptual perspective in the generation of
    plural referring expressions. Journal of Logic
    Language and Information (JoLLI) 16 (4),
    p.423-444.

3
some received wisdom
  • Choice is ultimately dependent on the
    perspective you decide to take on the referent
    (...).
  • Will it be more effective for me to refer to my
    sister as my sister or as that lady or as the
    physicist ? (Levelt 99, p. 226)

4
the rest of this talk
  • Generation of Referring Expressions
  • Perspective and Conceptual Coherence
  • reference to sets (van Deemter 2002)
  • experimental work
  • An algorithm
  • evaluation
  • Extensions
  • local (Conceptual) Coherence in discourse

5
Generation of Referring Expressions (GRE)
  • Part of micro-planning (Reiter/Dale 00)
  • At this stage, the content of a message is being
    determined, including descriptions of domain
    objects (Noun Phrases)
  • The task of GRE
  • given a set of intended referents, look up
    properties of these referents that will
    distinguish them from their distractors in a
    Knowledge Base

6
Content determination strategies
entity base type occupation specialisation girth
e1 woman professor physicist Plump
e2 woman lecturer geologist thin
e3 man lecturer biologist plump
e4 man postgraduate thin
  • Most algorithms inspired by the Gricean maxims
    (Grice 75)
  • especially Brevity (Dale 89, Gardent 02)
  • But compare
  • ?? ?x professor(x) V plump(x)
  • ?? ?x professor(x) V plump(x) man(x)
  • ? ?x biologist(x) V physicist(x)
  • All are equally brief, but not all have an
    equally good ring to them.

7
the Conceptual Coherence constraint
  • Sets (and disjunction) ?x p(x) V q(x) the p
    and the q
  • reference to a plurality suggests to the listener
    that there is a relationship holding between
    elements of the pluralities
  • p and q should be related or similar
  • semantic relatedness allows the listener to
    conceptualise the plurality more easily (Sanford
    and Moxey, 95)
  • Gatt and van Deemter (02)
  • Peoples preference for descriptions of this form
    were highly correlated to the semantic similarity
    of disjuncts
  • Best results achieved with a distributional
    definition of similarity (Lin 98)
  • sim(w,w) is a function of how often w and w
    occur in the same grammatical relations in a
    corpus

8
Lins definition of distributional similarity
  • Let w1, w2 be two words of the same grammatical
    category.
  • E.g. dog, cat
  • Let F(w) GR1,,GRn be the set of grammatical
    relations w occurs in, where
  • GRi ltwi, R, x, I(w,x)gt
  • wi the target word, R the relation, x the
    co-argument of w
  • I(wi,x) is the probability of wi and x occurring
    in this construction (as mutual information).
  • Example ltdog, modified-by, straygt
  • sim(w1, w2) is calculated using the GR triples
    that w1 and w2 share.
  • We use SketchEngine, a large-scale implementation
    of this theory, based on the BNC (Kilgarriff,
    03)

9
experiment 1 multimodal sentence completion
  • General idea
  • To refer to a set, people will prefer to use a
    plural that respects the conceptual coherence
    constraint
  • If this is impossible, then they will prefer to
    refer to the individuals in the set separately.
  • Experimental domains
  • 3 targets (a,b,c) 1 distractor (d)
  • sim(a,b) could be high or low
  • sim(a,c) sim(b,c) low
  • Expectation
  • if 2 of the targets have semantically similar
    types, they will be referred to in a plural
    description
  • reference to any two targets in case similarity
    is constant is no better than chance

10
experiment 1 example domain
  • Experimental domain
  • Participants completed the sentences by clicking
    on the pictures.
  • Manipulation of similarity of two of the objects
    (a,b).
  • Hypothesis
  • If a,b are similar, they are more likely to be
    referred to in the plural.

a
d
c
b
Complete the following by clicking on the
pictures
The _____________ and the _____________ cost 5.
The _____________ also costs 5.
11
experiment 1 results
Proportion of plural references to designated
targets a,b when
12
experiment 2 sentence continuation
  • Does similarity play a role in content
    determination?
  • Distinguishing properties nouns (12) or
    adjectives (12 ).
  • Expectation
  • Participants will select similar properties in
    the plural description, even though the
    alternative would also constitute a successful
    reference.

A university building was robbed last night. The
police have detained three suspects for
questioning, all of whom work or study at the
university. 1. One of them is a postgraduate. He
is a physicist. 2. Another is, a Greek, an
undergraduate. 3. Also among the suspects is a
cleaner. He is an Italian. Both
______________________ were held in custody, but
the physicist was released last night.
13
experiment 2 results
Proportion of references using pairwise similar
properties
Nouns
Adjectives
Friedman 45.89, p lt .001 trend as expected
Friedman 36.3, p lt .001 trend in the opposite
direction
14
summary of findings so far
  • In referential situations, people prefer to
    produce plural descriptions if the entities can
    be conceptualised under the same perspective.
  • This holds for types, but not modifiers
  • Types correspond to concepts, and are the way
    we carve up the world and categorise objects
  • Modifiers correspond to properties of those
    objects.
  • Results have been corroborated in other
    experiments

15
a GRE algorithm
  • Main knowledge source
  • The relation sim (which is based on the BNC-based
    lexical database of Kilgarriff 03)
  • Input
  • Knowledge base
  • Target referents (R )

16
step 1
  • Lexicalise properties in the KB
  • Identify types (nominal properties) and modifiers
  • The set of types and the similarity relation
    define a semantic space S ltT, simgt
  • Definition 1 Perspective
  • A perspective P is a convex subset of S, i.e.
  • ? t, t, t ? T
  • t, t ? P sim(t, t) sim(t, t) ? t ? P
  • Computed using a clustering algorithm (Gatt 06),
    which recursively groups together semantic
    nearest neighbours.

17
perspective graph
  • Aim find a description for R that minimises the
    distance between perspectives from which
    properties are selected.
  • Weight of a description, w(D) the sum of
    distances between perspectives represented in D.
  • w( the professor and the plump man ) 1
  • w( the biologist and the physicist ) 0

18
descriptive coherence
  • Definition 2 Maximal coherence
  • D is maximally coherent if there is no D
    coextensive with D such that w(D) lt w(D)
  • implies finding a shortest connection network in
    the perspective graph (intractable!)
  • Definition 3 Local coherence
  • D is locally coherent if there is no D
    coextensive with D s.t.
  • D is obtained by replacing a perspective in D
  • w(D) lt w(D)

19
search procedure
  • N ? Ø //the perspectives represented in D
  • root ? perspective with most referents in its
    extension
  • starting from root do
  • Check types and modifiers.
  • If a property excludes distractors
  • add it to D
  • add the perspective to N
  • If R is not distinguished, go to the next
    perspective, which is

(V is the set of perspectives).
20
evaluation
  • Do people prefer coherence over brevity?
  • (Two Gricean maxims Be brief vs. Be orderly)
  • Method subjects (N 39) shown 6 discourses.
  • Each discourse introduces 3 entities
  • Followed by 2 possible continuations
  • Subjects had to indicate their preferred
    continuation
  • Each of the 6 discourses represented a condition
  • Brevity descriptions equally (in-)coherent, but
    one is brief
  • Coherence descriptions equally (non-)brief only
    one is coherent
  • Trade-off coherent description is non-brief

21
results preference for brevity
both descriptions coherent x2 .023, p .8
both descriptions non-coherent x2 .64, p .4
22
results preference for coherence
both descriptions non-minimal x2 13.56, p lt .001
both descriptions minimal x2 16.03, p lt .001
23
results trade-off
coherent non-minimal x2 39.0, p lt .001
24
Conclusion
  • Perspectives on perspectives
  • Aloni (2002) answers to questions wh x? must
    conceptualise the different x using one and the
    same perspective (relevant given hearers
    information state and the context)
  • GvD (2007)
  • perspective defined (via lexical similarity)
  • when its impossible to use the same perspective,
    use perspectives that are similar

25
Methodology
  • Many experiments were done
  • to find a suitable notion of similarity/coherence
  • to discover how coherence and brevity relate
  • Surprise coherence more important than brevity
    (in the cases investigated!) no effect of
    brevity was found
  • Yet, different algorithmic interpretations would
    be possible
  • Algorithms are almost always under-determined by
    the empirical evidence

26
This is a lexical approach
  • Advantage empirical resources for determining
    similarity/coherence are readily available
  • Disadvantage the relation with classic (i.e.,
    linguistic or real-AI) notions of perspective
    and relevance is unclear
  • (A modest move towards reconciliation the root
    could be chosen using some notion of relevance)

27
A limitation
  • Ambiguity/polysemy is not taken into account
  • For example, we might generate
  • the river and the/its bank
  • These issues investigated in Imtiaz Khans PhD
    project
  • One remark river might disambiguate bank

28
An open question
  • Why doesnt coherence play the same role for
    modifiers as for types?

29
Work in progress discourse coherence
  • The algorithm has been extended with a discourse
    model, which keeps track of previous references.
  • Currently experimenting with a model of discourse
    coherence
  • when generating a new reference, prefer the
    perspectives that have been used in the previous
    n utterances
  • Problems
  • verifying this empirically
  • defining n (cf. Centering Theory)
About PowerShow.com