Wiktionary Normalization of Translations and Morphological Information

What it is about

The paper extends the Yawipa Wiktionary parser to read translations from etymology glosses and morphological form-of relations. The etymology glosses add 282,092 new unique translations, a 5.9% increase, and the English Wiktionary dump yields 4,027,201 form-of relations across 168 relation types. The argument numbers in the etymology templates make it possible to flag annotation typos: a t11 argument is unlikely unless t1 to t10 are present. The extracted data are then used for three word-formation tasks: clipping (math from mathematics), contraction (I'm from I am) and eye dialect (spellings such as "aftuh"). Each task has about 1 to 2K instances. A character sequence model with copy attention beats one with standard attention by up to 52% in exact-match accuracy. Its errors are often only 1 or 2 characters from the gold form.

Ideas

• I1. en/src/tok.rs: add a deterministic rule set for English contractions (I'm, n't, 's, 'll), and measure the exact-match rate on the contraction tokens of EWT test. The tokenizer currently scores 90.0% on EWT, so the contraction subset is the place to look.
• I2. en/src/lexgen.rs: flag lexicon entries with a missing earlier part where a numbered component is present, following the paper's typo check. Hand-check the flagged entries and report how many are real typos.
• I3. en/src/morph.rs: a lexicon-driven clipping link (mathematics to math, telephone to phone) with a list of English clipping pairs written from our own lists. Measure precision and recall on a held-out list, with a negative control of random word pairs.

For Mova

The code is en/src/tok.rs for contractions, en/src/lexgen.rs for the typo check, and en/src/morph.rs for clipping. The check is en tok-eval for the first and en morph-eval for the other two. The chapter is 07. Punctuation, capital letters, abbreviations and numbers for contractions and 18-compounding-conversion-minor.md for clipping. The paper's models are neural and its data is Wiktionary (CC BY-SA), so use only the rules and the test design. Measure first: exact-match on EWT contraction tokens, two identical runs before any claim.

Cite

The paper itself, not this card. BibTeX from the library's record of the work. DOI 10.18653/v1/2020.coling-main.413

@inproceedings{wu2020wiktionary,
  title = {{Wiktionary Normalization of Translations and Morphological Information}},
  author = {Wu, Winston and Yarowsky, David},
  booktitle = {COLING 2020 (Barcelona, online)},
  year = {2020},
  doi = {10.18653/v1/2020.coling-main.413},
  url = {https://doi.org/10.18653/v1/2020.coling-main.413}
}

References

28 references, 1 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Judit Ács. 2014. Pivot-based multilingual dictionary building using Wiktionary. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14), pages 1938–1942, Reykjavik, Iceland, May. European Language Resources Association (ELRA). find
2. Julian Brooke, Tong Wang, and Graeme Hirst. 2011. Predicting word clipping with latent semantic analysis. In Proceedings of 5th International Joint Conference on Natural Language Processing, pages 1392–1396, Chiang Mai, Thailand, November. Asian Federation of Natural Language Processing. find
3. Ela Elsholz, Jon Chamberlain, and Udo Kruschwitz. 2019. Exploring language style in chatbots to increase perceived product value and user engagement. In Proceedings of the 2019 Conference on Human Information Interaction and Retrieval, pages 301–305. find
4. Fadhl Eryani, Nizar Habash, Houda Bouamor, and Salam Khalifa. 2020. A spelling correction corpus for multiple Arabic dialects. In Proceedings of The 12th Language Resources and Evaluation Conference, Marseille, France, May. European Language Resources Association. find
5. Kyle Gorman, Lucas F.E. Ashby, Aaron Goyzueta, Arya McCarthy, Shijie Wu, and Daniel You. 2020. find
6. The SIGMORPHON 2020 shared task on multilingual grapheme-to-phoneme conversion. In Proceedings of the 17th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology, pages 40–50, Online, July. Association for Computational Linguistics. find
7. Jiatao Gu, Zhengdong Lu, Hang Li, and Victor O.K. Li. 2016. Incorporating copying mechanism in sequence-to-sequence learning. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1631–1640, Berlin, Germany, August. Association for… find
8. Marcelo Yuji Himoro and Antonio Pareja-Lora. 2020. Towards a spell checker for zamboanga chavacano orthography. In Proceedings of The 12th Language Resources and Evaluation Conference, Marseille, France, May. European Language Resources Association. find
9. Katharina Kann, Arya D. McCarthy, Garrett Nicolai, and Mans Hulden. 2020. find
10. The SIGMORPHON 2020 shared task on unsupervised morphological paradigm completion. In Proceedings of the 17th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology, pages 51–62, Online, July. Association for Computational Linguistics. find
11. Christo Kirov, John Sylak-Glassman, Roger Que, and David Yarowsky. 2016. Very-large scale parsing and normalization of Wiktionary morphological paradigms. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16), pages 3121–3126, Portorož, Slovenia, May. E… find our card
12. Christo Kirov, Ryan Cotterell, John Sylak-Glassman, Géraldine Walther, Ekaterina Vylomova, Patrick Xia, Manaal Faruqui, Sabrina J. Mielke, Arya McCarthy, Sandra Kübler, David Yarowsky, Jason Eisner, and Mans Hulden. 2018. UniMorph 2.0: Universal morphology. In Proceedings of the Eleventh Internati… find
13. Guillaume Klein, Yoon Kim, Yuntian Deng, Jean Senellart, and Alexander Rush. 2017. OpenNMT: Open-source toolkit for neural machine translation. In Proceedings of ACL 2017, System Demonstrations, pages 67–72, Vancouver, Canada, July. Association for Computational Linguistics. find
14. Vivek Kulkarni and William Yang Wang. 2018. Simple models for word formation in slang. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 1424–1434, New Orleans, Louisiana, J… find
15. Jackson L. Lee, Lucas F.E. Ashby, M. Elizabeth Garza, Yeonju Lee-Sikka, Sean Miller, Alan Wong, Arya D. McCarthy, and Kyle Gorman. 2020. Massively multilingual pronunciation modeling with WikiPron. In Proceedings of The 12th Language Resources and Evaluation Conference, pages 4223–4228, Marseille, F… find
16. Matthias Liebeck and Stefan Conrad. 2015. IWNLP: Inverse Wiktionary for natural language processing. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 41… find
17. Thang Luong, Hieu Pham, and Christopher D. Manning. 2015. Effective approaches to attention-based neural machine translation. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 1412–1421, Lisbon, Portugal, September. Association for Computational Linguis… find
18. Arya D. McCarthy, Ekaterina Vylomova, Shijie Wu, Chaitanya Malaviya, Lawrence Wolf-Sonkin, Garrett Nicolai, Christo Kirov, Miikka Silfverberg, Sabrina J. Mielke, Jeffrey Heinz, Ryan Cotterell, and Mans Hulden. 2019. find
19. The SIGMORPHON 2019 shared task: Morphological analysis in context and cross-lingual transfer for inflection. In Proceedings of the 16th Workshop on Computational Research in Phonetics, Phonology, and Morphology, pages 229–244, Florence, Italy, August. Association for Computational Linguistics. find
20. Arya D. McCarthy, Christo Kirov, Matteo Grella, Amrit Nidhi, Patrick Xia, Kyle Gorman, Ekaterina Vylomova, Sabrina J. Mielke, Garrett Nicolai, Miikka Silfverberg, Timofey Arkhangelskiy, Nataly Krizhanovsky, Andrew Krizhanovsky, Elena Klyachko, Alexey Sorokin, John Mansfield, Valts Ernštreits, Yuval… find
21. Clifton McFate and Kenneth Forbus. 2011. NULEX: An open-license broad coverage lexicon. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pages 363–367, Portland, Oregon, USA, June. Association for Computational Linguistics. find
22. V. Nastase and C. Strapparava. 2015. knowitiary: A machine readable incarnation of wiktionary. Int. J. Comput. Linguistics Appl., 6:61–82. find
23. Emmanuel Navarro, Franck Sajous, Bruno Gaume, Laurent Prévot, ShuKai Hsieh, Ivy Kuo, Pierre Magistry, and Chu-Ren Huang. 2009. Wiktionary for natural language processing: Methodology and limitations. In Proceedings of the 2009 Workshop on The People’s Web Meets NLP: Collaboratively Constructed Sema… find
24. Garrett Nicolai and David Yarowsky. 2019. Learning morphosyntactic analyzers from the Bible via iterative annotation projection across 26 languages. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 1765–1774, Florence, Italy, July. Association for Com… find
25. Franck Sajous, Basilio Calderone, and Nabil Hathout. 2020. ENGLAWI: From human- to machine-readable Wiktionary. In Proceedings of the 12th Language Resources and Evaluation Conference, pages 3016–3026, Marseille, France, May. European Language Resources Association. find
26. Gilles Sérasset. 2015. Dbnary: Wiktionary as a lemon-based multilingual lexical resource in rdf. Semantic Web, 6(4):355–361. find
27. Martin Volk and Rico Sennrich. 2011. Disambiguation of English contractions for machine translation of TV subtitles. In Proceedings of the 18th Nordic Conference of Computational Linguistics (NODALIDA 2011), pages 238–245, Riga, Latvia, May. Northern European Association for Language Technology (NEA… find
28. Winston Wu and David Yarowsky. 2020. Computational etymology and word emergence. In Proceedings of The 12th Language Resources and Evaluation Conference, pages 3252–3259, Marseille, France, May. European Language Resources Association. find

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/lex-2020-wu-wiktionary-normalization/