context-sensitive description of objects

25
1 Context-sensitive description of objects Mariët Theune (joint work with Emiel Krahmer)

Upload: palti

Post on 05-Jan-2016

27 views

Category:

Documents


2 download

DESCRIPTION

Context-sensitive description of objects. Mari ë t Theune (joint work with Emiel Krahmer). Introduction. An important question: How to generate distinguishing descriptions of objects? State of the art: Incremental Algorithm, Dale & Reiter (1995) Today’s aims: - PowerPoint PPT Presentation

TRANSCRIPT

Page 1: Context-sensitive description of objects

1

Context-sensitive description of objects

Mariët Theune(joint work with Emiel Krahmer)

Page 2: Context-sensitive description of objects

2

Introduction

An important question:How to generate distinguishing descriptions of objects?

State of the art: Incremental Algorithm, Dale & Reiter (1995)

Today’s aims:• Show that Dale and Reiter’s algorithm can be refined by taking salience into account• … which opens the way for several interesting

extensions

Page 3: Context-sensitive description of objects

3

Overview

• Dale & Reiter’s Incremental Algorithm• A modified Incremental Algorithm• Extensions:

– Pronouns– Relational descriptions

• Implementation • Evaluation• Concluding remarks • Related work

Page 4: Context-sensitive description of objects

4

The Incremental Algorithm

Terminology

Distinguishing description

An accurate description of the intended referent r, but

not of any other object in the current context set

Distractors

The objects from which r has to be distinguished (= all

objects other than r)

Page 5: Context-sensitive description of objects

5

Terminology (cont.)

Preferred attributes

The properties that human speakers and hearers prefer

for a specific domain

Best value

The value that is closest to the basic level value of a

property, and that still rules out the maximal number of

distractors

Page 6: Context-sensitive description of objects

6

The Incremental Algorithm

Strategy

Iterate through the list of preferred attributes,

• adding the best value of an attribute if: - it rules out any distractors not previously ruled out - or the attribute is ‘type’

• terminating when a distinguishing description has been constructed (all distractors have been ruled out)

Page 7: Context-sensitive description of objects

7

The Incremental Algorithm

Example

Domain (Dale & Reiter 1995:258):

d1 <type, chihuahua>, <size, small>, <colour, black>

d2 <type, chihuahua>, <size, large>, <colour, white>

d3 <type, siamese cat>, <size, small>, <colour, black>

Preferred attributes: < type, colour, size >

Page 8: Context-sensitive description of objects

8

Example (cont.)

animal

DOG CAT d1

chihuahua poodle siamese cat

Describe d2:1. Property ‘type’, best value = ‘dog’ d2

2. Property ‘colour’, best value = ‘white’

d3Result: < white, dog >

Page 9: Context-sensitive description of objects

9

The Incremental Algorithm

Good points

• Fast and efficient due to lack of backtracking• Psychologically realistic

Still lacking

• Construction of natural language expressions• Context sensitivity

Page 10: Context-sensitive description of objects

10

A modified algorithm

Adding salience

Intuition

A definite description refers to the most salient object

which has the properties expressed by it

Salience (Lewis 1979):The dog got in a fight with another dog

Page 11: Context-sensitive description of objects

11

Adding salience (cont.)

Salience weights (sw)

In each state, every object is assigned a natural number

between 0 (not salient) and 10 (maximally salient)

Salience weight assignment• In the initial state, salience weight is 0 for all objects• If an object is mentioned, its salience weight increases• If an object is not mentioned, its salience weight

decreases (to a minimum of 0)

Page 12: Context-sensitive description of objects

12

A modified algorithm

Strategy

Same as the Incremental Algorithm, except:

• The distractors are those objects in the domain with a salience weight that is equal to or higher than that of the intended referent

• An NP tree is built within the algorithm, to check the expressibility of properties (cf. Horacek 1997)

Page 13: Context-sensitive description of objects

13

A modified algorithm

Example (1) d1

Input:

• Object r = d2 d2

• State s0 :

sw(d1)= sw(d2) = sw (d3) = 0

• P = < type, colour, size … > d3

• L = <>

Result: the2 white dog

Page 14: Context-sensitive description of objects

14

A modified algorithm

Example (2) d1

Context = The2 white dog and the3 cat …

Input

• Object r = d2 d2

• State s : sw(d2)= sw(d3) > sw (d1)

• P = < type, colour, size … >

• L = <> d3

The2 dog …

Page 15: Context-sensitive description of objects

15

A modified algorithm

Example (3) d4

Context = The2 white chihuahua …

Input d2

• Object r = d2

• State s : sw(d2) > sw (d1,3,4) d1

• ... d3

The2 dog …

Page 16: Context-sensitive description of objects

16

Extensions

PronounsIf• r is currently the single most salient object • and there is an antecedent for r

Then pronominalise reference to r

The2 white chihuahua was fast asleep.

It2 was dreaming of tasty bones.

Page 17: Context-sensitive description of objects

17

Extensions

Relational descriptions

• Add relations as attributes• Add a hierarchy of relations spatial

NEXT_TO IN

left_of right_of

If a relation with object r’ is included when describing r,then recursively call the algorithm to describe r’

Page 18: Context-sensitive description of objects

18

Relational descriptions (cont.)

Input: d2 , s0 , P = <type, …, spatial>, L = <>

• First property rules out d1 and d4, best value is ‘dog’

• Next properties (‘colour’, ‘size’) rule nothing out

• The spatial relation rules out d3; best value ‘next to’

d1 d2 d3 d4

Page 19: Context-sensitive description of objects

19

Relational descriptions (cont.)

Recursive call, input: d1, s0 , P, L = < next_to (d2,d1) >

• The spatial relation in L rules out all distractors• The ‘type’ property is included by default

• Resulting description of d1: the snowman

d1 d2 d3 d4

Page 20: Context-sensitive description of objects

20

Relational descriptions (cont.)

Recursive call, input: d1, s0 , P, L = < next_to (d2,d1) >

• The spatial relation in L rules out all distractors• The ‘type’ property is included by default

• Resulting description of d1: the snowman

d1 d2 d3 d4

The2 dog next to the1 snowman

Page 21: Context-sensitive description of objects

21

Implementation

The modified algorithm has been implemented in LGM,

IPO’s data-to-speech system. Applications of LGM are:

• DYD: information about Mozart compositions • GoalGetter: soccer reports • OVIS: train time information• VODIS: in-car route descriptions • Pavlov: toy system, testing the modified algorithm

Page 22: Context-sensitive description of objects

22

Evaluation

The basic assumptions underlying the modifiedalgorithm are that an anaphoric reference:

1. Contains fewer properties2. Uses more general phrasing3. Is pronominalised whenever possible4. Obeys 1 and 2 also after an intervening sentence

All hypotheses were experimentally confirmed, except 2(which turns out to depend on wording)

Page 23: Context-sensitive description of objects

23

Concluding remarks

Context Description

-

the white chihuahua

the black and the white chihuahua

the white chihuahua

the dog / it

the white dog

Use of salience allows for the generation of

context-sensitive descriptions:

Page 24: Context-sensitive description of objects

24

Related work

Krahmer, van Erk & Verleg (2001):• Domain represented as a labeled, directed graph• Property selection is subgraph construction

d1 d2 d3

d3

white

dog

dog

white

d2

d1

snowmannext-to

dog

snowmannext-to

Page 25: Context-sensitive description of objects

25

Related work

Van der Sluis & Krahmer (in progress): generating

referring expressions in a multi-modal context

• Three kinds of salience: linguistic, inherent, and focus space salience

• Pointing decision and determiner choice are added

that white one left of the blue one

* *this blue one