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

8. Results for classification (COG_FF/UNREL)

9. Results for classification (COG_FF/UNREL)

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 Foreach 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 forhumans • 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!