The document proposes a framework called Term Ambiguity Detection (TAD) to determine whether terms are ambiguous or unambiguous at the term level rather than at the instance level. The TAD framework uses a three step process: (1) an n-gram method to check for common words/phrases, (2) an ontology method using Wiktionary and Wikipedia to check for multiple senses or disambiguation pages, and (3) a clustering method using LDA to check if category terms appear in document clusters. Evaluation on movie, video game, camera and book terms showed the combined framework achieved a high F-measure of 0.96 for ambiguity detection, allowing information extraction systems to achieve high precision by incorporating ambiguity information.
4. Find tweets about the movie Brave:
Movie night watching brave with Cammie n Isla n
loads munchies
This brave girl deserves endless retweets!
Watching brave with the kiddos!
watching Bregor playing Civ 5: Brave New World and
thinking of getting it
5. Skyfall 007 in class with @MariaWiheelste
So I was dead set on seeing skyfall 007 for like a year
NowWatching #skyFall 007!
What movie amazed u — skyfall 007
6. Existing Disambiguation Methods
Word Sense Disambiguation (WSD)
Which word sense does this instance refer to?
Named Entity Disambiguation (NED)
Which entity type is this instance associated with?
7. Existing Disambiguation Methods
Word Sense Disambiguation (WSD)
Which word sense does this specific instance refers to?
Named Entity Disambiguation (NED)
Which entity type is this individual instance associated with?
Limitations:
Assume the number of senses/entities is known
− Often not the case
Inefficient on very large data sets
− Attempt to disambiguate each instance
8. Term Ambiguity Detection (TAD)
Perform term disambiguation at the term, not
instance level
Given a term T and its category C, do all the
mentions of the term reference a member of that
category?
9. Term Ambiguity Detection (TAD)
Perform term disambiguation at the term, not instance
level
Given a term T and its category C, do all the
mentions of the term reference a member of that
category?
Level of ambiguity of the term
Hybrid information extraction (IE) systems
− Simpler model if the term unambiguous
− More complex model otherwise
Potentially useful for other NLP tasks
10. Term Ambiguity Detection (TAD)
CameraEOS 5D
Video Game
A New Beginning
MovieSkyfall 007
MovieBrave
CategoryTerm
Video Game
A New Beginning
MovieBrave
CategoryTerm
Ambiguous
CameraEOS 5D
MovieSkyfall 007
CategoryTerm
Unambiguous
TAD
12. TAD Framework
Step 1: N-gram
Does the term share a name
with a common word/phrase?
1. Normalize input term t
(stopword removel + lowercase)
2. Calculate unigram probability
3. Ambiguous if the probability is
above the empirically
determined threshold
Ambiguous
Unambiguous
13. TAD Framework
Step 1: N-gram
Step 2: Ontology
• Wiktionary:
Ambiguous if term has several
senses in Wiktionary
• Wikipedia:
Ambiguous if term has a
Wikipedia disambiguation page
Ambiguous
Unambiguous
14. TAD Framework
Step 1: N-gram
Step 2: Ontology
Step 3: Clustering
Cluster the contexts in which
the term appear
Ambiguous
Unambiguous
1. Remove stopwords and infrequent
words from all documens
containing the term
2. Cluster the document using Latent
Dirichlet Allocation (LDA)
3. Ambiguous if category term or
WordNet synonym does not appear
in the most heavily weighted terms
of any cluster
15. Evaluation
Dataset: terms from 4 product domains:
Movies, Video Games, Cameras, Books
− 100 terms per domain
− Extracted randomly from dbpedia and Flickr
Gold standard: ambiguity determined by
examining usage in TREC Tweets2011 corpus
10 tweets labeled per term
− Unambiguous only if all tweets reference category
17. Results - Effectiveness
Each module produced above baseline performance
Configuration Precision Recall F-measure
Majority Class 0.675 1.0 0.806
N-gram (NG) 0.979 0.848 0.909
Ontology (ON) 0.979 0.704 0.819
Clustering (CL) 0.946 0.848 0.895
NG + ON 0.980 0.919 0.948
NG + CL 0.942 0.963 0.952
ON + CL 0.945 0.956 0.950
All 0.943 0.978 0.960
18. Results - Effectiveness
Ontology method is of limited usage, as most of the
terms cannot be found in the ontology.
Configuration Precision Recall F-measure
Majority Class 0.675 1.0 0.806
N-gram (NG) 0.979 0.848 0.909
Ontology (ON) 0.979 0.704 0.819
Clustering (CL) 0.946 0.848 0.895
NG + ON 0.980 0.919 0.948
NG + CL 0.942 0.963 0.952
ON + CL 0.945 0.956 0.950
All 0.943 0.978 0.960
19. Results - Effectiveness
Each module produced above baseline performance
Combined framework produced high F-measure of 0.96
Configuration Precision Recall F-measure
Majority Class 0.675 1.0 0.806
N-gram (NG) 0.979 0.848 0.909
Ontology (ON) 0.979 0.704 0.819
Clustering (CL) 0.946 0.848 0.895
NG + ON 0.980 0.919 0.948
NG + CL 0.942 0.963 0.952
ON + CL 0.945 0.956 0.950
All 0.943 0.978 0.960
20. Results - Usefulness
Integrated TAD pipeline into commercially
available IE system
Extracted mentions of terms from Camera and
Video game domains on Twitter data
Manually judged relevance of extracted Tweets
21. Results - Usefulness
Using ambiguity detection hurt recall
Only 57% of the relevant documents returned
with TAD
Ambiguity detection necessary for high
precision
w/ ambiguity detection:
− Precision: 0.96
w/o ambiguity detection
− Precision: 0.16
22. Conclusion
Term ambiguity detection is helpful for large-
scale information extraction
Able to detect ambiguity when number of senses is
unknown
Able to be applied to large datasets where instance-
level interpretation is impractical
3-Module TAD approach results is high
performance
Detects ambiguity with F-measure of 0.96
Allows IE system to produce high precision