Measuring Adaptation Between Dialogs - - PowerPoint PPT Presentation

measuring adaptation between dialogs
SMART_READER_LITE
LIVE PREVIEW

Measuring Adaptation Between Dialogs - - PowerPoint PPT Presentation

Measuring Adaptation Between Dialogs


slide-1
SLIDE 1
  • Measuring Adaptation

Between Dialogs

slide-2
SLIDE 2
  • Adaptation in Dialog

!"#$###

#"%%#&''#' (' )*"'$' !"&#'#

#'

slide-3
SLIDE 3
  • +

Examples of Lexical Variation

,-. ,'$. ,(%''. ,$. ,". ,#'. ,/#'. ,!$.

slide-4
SLIDE 4
  • Examples of Lexical Variation

,-. ,'$. ,(%''. ,$.

slide-5
SLIDE 5
  • 1

Examples of Syntactic Variation

  • ,)"2 3.

,)"32 .

slide-6
SLIDE 6
  • 4

Evidence of Adaptation in Dialog

5#%&#'6

,&###2###'#"2

'#'###'# ##" '#.

/%#"&''#' ##'

! "#

slide-7
SLIDE 7
  • Causes of Adaptation

/

7$%#& !%'(() %*

(#

%+!%'(('

  • '#'#"2$

''###"

slide-8
SLIDE 8
  • 8

Recency

9'$#""$"

$#

'6"##"

#"

  • 7 ':';8<

,%$#$$ #"' '#$'$'## :''$.

slide-9
SLIDE 9
  • ;

Partner Adaptation

'% '6#$#'#"

,"2$ %#'2$#=.> ''6

$' 2''##$'

'''

slide-10
SLIDE 10
  • Corpus Studies On Recency

Adaptation

?!$@'$&##

,##$. #%# '

?$2 >>4@##''$

'$'####"' #&

?/# > 4@'$#''*

##"%%#3' $'#""#'# "''#

$ ##%

*'#%# #

slide-11
SLIDE 11
  • Setup

+' '6!

>

*A #'#2

>

*A! ' %%

+>

*A ' %%

  • !##
  • !#+#
slide-12
SLIDE 12
  • Maptask Corpus Structure

2 2 8

  • 2

4

  • 2
  • 1
  • 2

2

  • +

#

  • 2
  • #

2

  • Hypothesis:

recency adaptation happens between (1-4) and (2-3) partner adaptation happens between (1-6) and (2-5)

slide-13
SLIDE 13
  • +

Church’s measure for adaptation

slide-14
SLIDE 14
  • Church’s measure for adaptation

9#'''%$$#%

$'>-'$#'#2 %,". ''

)#"22##%$',.,.

$ #'$'

B(#B('##B #%

slide-15
SLIDE 15
  • 1

Proposed Adaptation Measure

  • * '$'

#>

C

'#'%#2 %$'2#"#'

C

#2'''

  • C

'#"%D$## %%'%D$#"

! #%%$#'# $%D$%# 'E#F #$##"

slide-16
SLIDE 16
  • 4

Proposed Adaptation Measures

slide-17
SLIDE 17
  • Terminology

'$%6GD$%%$%# $#'"2'# " "%D$% %$%#$' #%#$'## #"#%D$"2'# ' #"

slide-18
SLIDE 18
  • 8

Adaptation Ratio

P T P∩T

Chance: probability that f co-occurs in prime and target by chance:

N – total number of (prime, target) dialog pairs P – number of prime dialogs where freq of f > b T – number of target dialogs where freq of f > b

ƒєPrime ƒєTarget ƒєPrime and ƒє Target All Dialog pairs

N

slide-19
SLIDE 19
  • ;

Adaptation Ratio

Adaptation Ratio = +adapt / chance

Positive Adaptation:

P T

P∩T

N – total number of (prime, target) dialog pairs P – number of prime dialogs where freq of f > b T – number of target dialogs where freq of f > b

ƒєPrime

ƒєTarget

ƒєPrime and ƒє Target

N - All Dialog pairs

Chance probability that f co-

  • ccurs in prime and target by

chance

slide-20
SLIDE 20
  • Adaptation Ratio

Adaptation Ratio = +adapt / chance

Positive Adaptation:

P T P∩T

N – total number of (prime, target) dialog pairs P – number of prime dialogs where freq of f > b T – number of target dialogs where freq of f > b

ƒєPrime ƒєTarget ƒєPrime and ƒє Target N - All Dialog pairs

slide-21
SLIDE 21
  • Adaptation Ratio

'$'#

C

'#'%# 2#%%%$'

C

#2%$'%#$' %D$#'

! #%%$#'# $%D$%# 'E#F #$##"

slide-22
SLIDE 22
  • Distance Measure

C '#"##"%%'

%D$#"6 %%$#'# #'#'&%D$# "H

slide-23
SLIDE 23
  • +

Distance Measure

For a feature f in a dialog pair (Prime, Target): t – frequency of feature f in target dialog p – frequency of feature f in prime dialog b – average frequency of f Feature f is “adapted” in a pair of dialogs if distance >0 Strength of adaptation is proportional to the distance

slide-24
SLIDE 24
  • Experimental Questions

>

#%%$'&#2# #> !2$'H

>

9#%##' 6H

+>

'%$%D$# ##"%%%$ %D$#"H

slide-25
SLIDE 25
  • 1

Features

9'#(I"'J

#'#"$#'2'''

#"' '#(I"' #7%3'

#'<

slide-26
SLIDE 26
  • 4

Word-Stems with Adaptation Ratio > 1 and significant

  • 2

I ' " '' K5/ %2 ''$" "% (/5( $ #

  • L

#M$' $''

  • 5-

#' #% !IL #"2$ #" K 2#"* #"* L

  • Only features occuring in > 30% of prime dialogs with freq > baseline

Relative direction Contains ‘you’ Contains ‘I’ or ‘my

slide-27
SLIDE 27
  • Bigrams with Adaptation Ratio > 1 and

significant

your left, right-hand side, come to, you come, about the, when you, go round, and round, you got, if you, up toward, a wee, you just, round the, right you, just abov, abov the no no, my map,

  • kay and,

you just,

  • n my,

down about, yeah i, you got, down to, have a, i mean, ’til you, just below, just to, now you, no you

Partner Recency

Relative direction Contains ‘you’ Contains ‘I’ or ‘my

Only features occuring in > 30% of prime dialogs with freq > baseline

slide-28
SLIDE 28
  • 8

Comparing Partner and Recency Adaptation

2.4 2.5 2.6 2.7 2.8 2.9 3 3.1 Word Bigram Syntactic Partner Recency

adaptation ratio and adaptation strength are averaged over all features for each feature type

Adaptation Ratio = +adapt / chance

0.5 1 1.5 2 2.5 3 3.5 4 4.5 5 Word Bigram Syntactic Partner Recency

Distance measure ~ Adaptation strength

* * * * * Indicates significance (p<.05)

slide-29
SLIDE 29
  • !

"#$

$%&'(&'(()

slide-30
SLIDE 30
  • ;

Adaptation Ratio for Selected Syntactic Features

0.5 1 1.5 2 2.5 3 3.5 NP->NP PP NP->NN NP->DT NN NP->DT AP NN Partner Recency

The features examined by Dubey et.al 2006 on Switchboard corpus Found adaptation between speakers

slide-31
SLIDE 31
  • +

Adaptation for Selected Syntactic Features

5 10 15 20 25 30 35 NP->NP PP NP->NN NP->DT NN NP->DT AP NN Partner Recency

NP->NN PP rule: adaptation ratio is stronger for recency means that if primed, speaker is more likely to use this rule in the very next conversation Adaptation Strength is higher for the partner scenario means that the “adapting speaker” in partner-scenario will use this rule with higher frequency than the “adapting speaker” in recency-scenario

0.5 1 1.5 2 2.5 3 3.5 NP->NP PP NP->NN NP->DT NN NP->DT AP NN Partner Recency

Adaptation Ratio = +adapt / chance Distance measure ~ Adaptation strength

slide-32
SLIDE 32
  • +

Dubey’s Results

slide-33
SLIDE 33
  • +

Effect of Frequency in the Prime

0.5 1 1.5 2 2.5 3 3.5 4 4.5 prime>base prime>base+1 prime>base+2 Partner Recency

#"

0.02 0.04 0.06 0.08 0.1 0.12 0.14 0.16 0.18 prime>base prime>base+1 prime>base+2 Partner Recency

N%%$' !$##%%$' !'#%$2,. #%#/#A

GD$%%$## '%%%# $%%''"%#

slide-34
SLIDE 34
  • ++

Conclusions

#%#'%%$'%%#"

##%%#$$'

G$#%%

#2#"'

###''"#

'#

###

'"'#

slide-35
SLIDE 35
  • +0

Implications

5#%# '$""''2%#'%

  • $#"'#"'7$

2$22###'<%#" ''#$$'

#"#%#2

'#""$""# $'

slide-36
SLIDE 36
  • +1

Future Work

9'$""'#'%

'$'$ #%%#2 #>

slide-37
SLIDE 37
  • +4

Future Work

'#'#*%D$

'

!'##%E F 3'$##*#"# !'#'$###"

#"%'#6

<*A<*A <*A<*A!

  • #$

'#' >

  • #$"=##
slide-38
SLIDE 38
  • +

O$'#'H

''# P"#>

  • $