Automatic Identification of Cognates, False Friends, and Partial Cognates

1
Automatic Identification of Cognates, False
Friends, and Partial Cognates

• University of Ottawa, Canada

2
Outline

• Overview of the Thesis
• Research Contribution
• Cognate and False Friend Identification
• Partial Cognate Disambiguation
• CLPA- Cognate and False Friend Annotator
• Conclusions and Future Work

3
Overview of the Thesis

• Tasks
• Automatic Identification of Cognates and False
  Friends
• Automatic Disambiguation of Partial Cognates
• Areas of Applications
• CALL, MT, Word Alignment, Cross-Language
  Information Retrieval
• CALL Tool - CLPA

4
Definitions

• Cognates or True Friends (Vrais Amis), are pairs
  of words that are perceived as similar and are
  mutual translations.
• nature - nature, reconnaissance -
  recognition
• False Friends (Faux Amis) are pairs of words in
  two languages that are perceived as similar but
  have different meanings.
• main (hand) - main (principal, essential),
  blesser (to injure) - bless (bénir in French)
• Partial Cognates words that share the same
  meaning in two languages in some but not all
  contexts
• note note, facteur - factor or mailman,
  maker

5
Research Contribution

• Novel method based on ML algorithms to identify
  Cognates and False Friends
• A method to create complete lists of Cognates and
  False Friends
• Define a novel task Partial Cognate
  Disambiguation, and solve it using a supervised
  and a semi-supervised method
• Combine and use corpora from different domains
• Implement a CALL Tool CLPA to annotate Cognates
  and False Friends

6
Cognates and False Friends Identification

• Our method
• Machine Learning techniques with different
  algorithms
• Instances French-English pairs of words
• Feature Space 13 orthographic similarity
  measures
• Classes Cog_FF and Unrelated
• Experiments done for
• Each measure separately
• Average of all measures
• All 13 measures

7
Cognates and False Friends Identification

• Data

Training set Test set
Cognates 613 (73) 603 (178)
False-Friends 314 (135) 94 (46)
Unrelated 527 (0) 343 (0)
Total 1454 1040
8
Results for classification (COG_FF/UNREL)
Orthographic similarity measure Threshold Accuracy on Training set Accuracy on Test set
IDENT 1 43.90 55.00
PREFIX 0.03845 92.70 90.97
DICE 0.29669 89.40 93.37
LCSR 0.45800 92.91 94.24
NED 0.34845 93.39 93.57
SOUNDEX 0.62500 85.28 84.54
TRI 0.0476 88.30 92.13
XDICE 0.21825 92.84 94.52
XXDICE 0.12915 91.74 95.39
TRI-SIM 0.34845 95.66 93.28
TRI-DIST 0.34845 95.11 93.85
Average measure 0.14770 93.83 94.14
9
Results for classification (COG_FF/UNREL)
Classifier Accuracy cross- val. on training set Accuracy on test set
Baseline 63.75 66.98
OneRule 95.66 92.89
Naive Bayes 94.84 94.62
Decision Tree 95.66 92.08
Decision Tree (pruned) 95.66 93.18
IBK 93.81 92.80
Ada Boost 95.66 93.47
Perceptron 95.11 91.55
SVM (SMO) 95.46 93.76
10
Complete Lists of Cognates and False Friends

• Method
• Use the XXDICE orthographic similarity measure
• Use list of pairs of words in two languages (the
  words that are translation of each other, or not,
  or monolingual lists of words)
• Use a bilingual dictionary to determine if the
  words contained in a pair are translation of each
  other

11
Complete Lists of Cognates and False Friends

• Evaluation
• On the entry list of a French-English bilingual
  dictionary
• 55 - Cognates
• 2 - False Friends (5,619,270 pairs)
• We created pair of words from two large
  monolingual list of words in French and English
• 11,469,662 Orthographical Similar (0.8)
• 3,496 Cognates (0.03)
• 3,767,435 False Friends (32)

12
Cognates and False Friends Identification

• Conclusion
• We tested a number of orthographic similarity
  measures individually, and also combined using
  different Machine Learning algorithms
• We evaluated the methods on a training set using
  10-fold cross validation, on a test set
• We proposed an extension of the method to create
  complete lists of Cognates and False Friends
• The results show that, for French and English, it
  is possible to achieve very good accuracy based
  on the orthographic measures of word similarity

13
Partial Cognate Disambiguation

• Task
• To determine the sense/meaning (Cognate or False
  Friend with the equivalent English word) of an
  Partial Cognate in a French context
• Note
• Cog
• Le comité prend note de cette information.
• The Committee takes note of this reply.
• FF
• Mais qui a dû payer la note?
• So who got left holding the bill?

14
Data

• Use a set of 10 Partial Cognates
• Parallel sentences that have on the French side
  the French Partial Cognate and on the English
  side the English Cognate (English False Friend) -
  labeled as COG (FF)
• Collected from EuroPar, Hansard
• 115 sentences each class for Training
• 60 sentences each class for Testing

15
Supervised Method

• Traditional ML algorithms
• Features
• - used the bag-of-words (BOW) approach of
  modeling context, with the binary feature values
• - context words from the training corpus that
  appeared at least 3 times in the training
  sentences
• Classes COG and FF

16
Monolingual Bootstrapping

• For each pair of partial cognates (PC)
• 1. Train a classifier on the training seeds
  using the BOW approach and a NB-K classifier
  with attribute selection on the features
• 2. Apply the classifier on unlabeled data
  sentences that contain the PC word, extracted
  from LeMonde (MB-F) or from BNC (MB-E)
• 3. Take the first k newly classified sentences,
  both from the COG and FF class and add them to
  the training seeds (the most confident ones
  the prediction accuracy greater or equal than a
  threshold 0.85)
• 4. Rerun the experiments training on the new
  training set
• 5. Repeat steps 2 and 3 for t times
• endFor

17
Bilingual Bootstrapping

• 1. Translate the English sentences that were
  collected in the MB-E step into French using an
  online MT tool and add them to the French seed
  training data.
• 2. Repeat the MB-F and MB-E steps for T times.

18
Additional Data

• LeMonde
• An average of 250 sentences for each class
• BNC
• An average of 200 sentences for each class
• Multi-Domain corpus
• An average of 80 sentences for each class

19
Results
20
Partial Cognate Disambiguation

• Conclusions
• Simple methods and available tools are used with
  success for a task hard to solve even for humans
• Additional use of unlabeled data improves the
  learning process for the Partial Cognates
  Disambiguation task
• Semi-Supervised Learning proves to be as good
  as Supervised Learning

21
CLPA-Cross Language Pair Annotator
22
Future Work

• Apply the Cognate and False Friend Identification
  method, and create complete list for other pair
  of languages
• Increase the accuracy results for the Partial
  Cognate Disambiguation task
• Use lemmatization for French texts and human
  evaluation for CLPA

23

• Thank you!