generation of referring expressions: managing structural ambiguities i.h. khang. ritchie k. van...
TRANSCRIPT
Generation of Referring Expressions: Managing Structural Ambiguities
I.H. Khan G. Ritchie K. van Deemter
University of Aberdeen, UK
A natural language generator should avoid generating those phrases, which are too ambiguous to understand. But, how the generator can know whether a phrase is too ambiguous or not? We use corpus-based heuristics, backed by empirical evidence, that estimate the likelihood of different readings of a phrase, and guide the generator to choose an optimal phrase from the available alternatives.
Process of generating text in natural language (e.g., English) from some non-linguistic data (Reiter & Dale, 2000)
Example NLG system
– Pollen Forecast: generates reports from pollen forecast data
Natural Language Generation (NLG)
Grass pollen levels for Tuesday have decreased from the high levels of yesterday with values of around 4 to 5 across most parts of the country. However, in South Eastern areas, pollen levels will be high with values of 6. [courtesy E. Reiter]
Referring Expression = Noun Phrase – e.g., the black cat; the black cats and dogs (etc.)
A key component in most NLG systems Task of GRE:
– Given a set of intended referents, compute the properties of these referents that distinguish them from distractors in a KB
Generation of Referring Expressions (GRE)
GRE: An Example
Objects PropertiesObject1 (Type, Sheep), (Color, Black)
Object2 (Type, Sheep), (Color, Brown)
Object3 (Type, Sheep), (Color, Black)
Object4 (Type, Goat), (Color, Black)
Object5 (Type, Goat), (Color, Yellow)
Object6 (Type, Goat), (Color, Black)
Object7 (Type, Goat), (Color, Brown)
Object8 (Type, Cow), (Color, Black) Output: Distinguishing Description (DD)
– (Black Sheep) (Black Goat)
KB
Input: KB, Intended Referents R
Task: find properties that distinguish R from distractors
The Problem
NP1: The black sheep and the black goats
NP2: The black sheep and goats
(Black Sheep) (Black Goat) = {Object1,Object3,Object4,Object6}
(Black Sheep) Goat = {Object1,Object3,Object4,Object5,Object6,Object7}
NP1 unambiguous and long; NP2 ambiguous and brief
Question: How the generator might chose between NP1 and NP2?
Linguistic ambiguities can arise when DDs are realised
Our Approach Psycholinguistic evidence
– Avoidance of all ambiguity is not feasible (Abney, 1996)
Avoid only distractor interpretations– An interpretation is distractor if it is more likely or almost as
likely as the intended one.
Question– How to make distractor interpretation precise?
Our solution– Getting likelihood using word sketches (cf. Chantree et el., 2004)
– Word sketches provide detailed information about word relationships, based on corpus frequencies
– Relationships are grammatical
Hypothesis 1– If Adj modifies N1 more often than N2, then a narrow-scope
reading is likely (no matter how frequently N1 and N2 co-occur).
bearded men and women handsome men and women
Hypothesis 2– If Adj does not modify N1 more often than N2, then a wide-
scope reading is likely (no matter how frequently N1 and N2 co-occur)..
old men and women tall men and trees
Pattern: the Adj N1 and N2
Experiment 1
Please, remove the roaring lions and horses.
Experiment 1: Results
Hypothesis 2 (i.e., predictions for WS reading) is confirmed
Hypothesis 1 (i.e., predictions for NS reading) is not confirmed
– Tendency for WS (even though results are not stat. sig.)
Tentative conclusion– An intrinsic bias in favour of WS reading
BUT: The use of *unusual* features may have made people’s judgements unreliable
Experiment 2
Please, remove the figure containing the young lions and horses.
Experiment 2 (cont.)
Please, remove the figure containing the barking dogs and cats.
Results: Both hypotheses are confirmed
Word Sketches can make reasonable predictions about how an NP would be understood.
But we need more to know from generation point of view: which of the following two NPs is best?
The black sheep and the black goats
The black sheep and goats
(Black Sheep) (Black Goat)
(Black Sheep) Goat
We seek the answer in next experiment
Clarity-brevity trade-off
Recall the pattern: the Adj Noun1 and Noun2
Brief descriptions (+b) take the form– the Adj Noun1 and Noun2
Non-brief descriptions (-b) take the form– the Adj Noun1 and the Adj Noun2 (IR = WS)
– the Adj Noun1 and the Noun2 (IR = NS)
Clear descriptions (+c)– Which have no distractor interpretations
Non-clear descriptions (-c)– Which have some distractor interpretations
Hypothesis 1
– (+c, +b) descriptions are preferred over (+c, -b)
Hypothesis 2
– (+c, -b) descriptions are preferred over (-c, +b)
Each hypothesis is tested under two conditions– C1: intended reading is WS
– C2: intended reading is NS
The Hypotheses (Readers’ Preferences)
Experiment 3: NS Case
Which phrase works best to identify the filled area?
1. The barking dogs and cats
2. The barking dogs and the cats
Experiment 3: WS Case
Which phrase works best to identify the filled area?
1. The young lions and the young horses
2. The young lions and horses
Experiment 3: Results
Both hypotheses are confirmed:
– (+c, +b) descriptions are preferred over (+c, -b)
– (+c, -b) descriptions are preferred over (-c, +b)
Role of length:
– In WS cases preferences are very strong
– In NS cases preference is not as strong as in WS cases
Summary of Empirical Evidence
For the pattern the Adj Noun1 and Noun2
– Word Sketches can make reliable predictions
– Keeping clarity the same, a brief NP is better than a longer one
Algorithm Development
Main knowledge sources
– WordNet (for lexicalisation)
– SketchEngine (for predicting the most likely reading)
Main steps
1. Choose words
2. Use these to construct description in DNF
3. Use transformations to generate alternative structures from DNF
4. Select optimal phrase
Transformation Rules
Input
– Logical formula in DNF
Rule Base
1.(A B1) (A B2) A (B1 B2)
2.(X Y) (Y X)
[A = Adj, B1=B2=Noun, X=Y=(Adj and/or Noun)]
Output
– Set of logical formulae
Select optimal phrase
1. (black sheep) (black goats) DNF2. (black goats) (black sheep)3. black (goats sheep)4. black (sheep goats) Optimal
(4): Adj has high collocational frequency with N1 and N2, so the intended (wide-scope) reading is more likely.
Therefore, (4) is selected.
Conclusions
GRE should deal with surface ambiguities Word sketches can make distractor interpretation precise Keeping clarity the same, brief descriptions are preferred
over longer ones A GRE algorithm is sketched that balances clarity and
brevity
THANK YOU