Elamur Research⌕
☰
home / papers / 2021 / Cross-Cultural Similarity Features for Cross-Lingual Transfer Learning of Pragmatically Motivated Tasks

Cross-Cultural Similarity Features for Cross-Lingual Transfer Learning of Pragmatically Motivated Tasks

Summary

Choosing a source language for cross-lingual transfer is usually guided by typological or genealogical closeness. The authors argue that this misses what matters for pragmatics-heavy tasks such as sentiment analysis, because culture shapes how emotion and figurative meaning are expressed. They propose three language-level measures intended as linguistic stand-ins for cultural similarity:

  • Language context-level ratio (LCR): derived from the share of pronoun and verb tokens in POS-tagged monolingual corpora.
  • Literal translation quality (LTQ): checks how well automatically mined multiword expressions survive word-by-word translation, using bilingual dictionaries and parallel text.
  • Emotion semantics distance (ESD): compares aligned cross-lingual embeddings of emotion words.

An intrinsic analysis over 16 languages shows that the features group languages in line with findings from sociolinguistics and linguistic anthropology. For example, Korean and Japanese come out as high-context and German and English as low-context. Incorporating the features into the LangRank transfer-language ranker yields better source-language choices when the task is sentiment analysis across languages, whereas dependency parsing sees no such gain. This supports the claim that cultural signals mainly help pragmatically driven tasks. The released code and data offer an early quantitative typology of pragmatics.

Key points

  • Resources used: NLTK and RDR POS Tagger, plus PyArabic, Jieba, Kytea and Mecab for Arabic, Chinese, Japanese and Korean. Corpora are the Leipzig news-crawl 1M corpora and TED talks corpora, with bilingual dictionaries from Choe et al. (2020).
  • LTQ setup: bigram and trigram MWEs are extracted with a PMI variant, keeping the top 500. Against Wiktionary idiom lists for English, French, German and Spanish, 19.0% of PMI bigrams and 3.8% of trigrams match gold MWEs.
  • ESD setup: builds on 24 emotion concepts from Jackson et al. (2019) and uses supervised cross-lingual embeddings following Lample et al. (2018). The emotion word pairs are removed from the alignment dictionary before aligning.
  • Controlled experiment: sentiment data were downsampled to match the Turkish dataset in size and label distribution, with Turkish as target. LangRank+Prag picked Arabic as the best source, which matches the ground truth. Plain LangRank preferred the typologically closer Japanese.
  • Availability: code and data are at github.com/hwijeen/langrank.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

Fields: Linguistics & languages

Cited by

18 papers of our library cite it (of the 140673 whose bibliographies we read); 2 of them have a page here, 16 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2021.eacl-main.204 · arXiv 2006.09336

@inproceedings{sun2021cross,
  title = {{Cross-Cultural Similarity Features for Cross-Lingual Transfer Learning of Pragmatically Motivated Tasks}},
  author = {Sun, Jimin and Ahn, Hwijeen and Park, Chan Young and Tsvetkov, Yulia and Mortensen, David R.},
  booktitle = {Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume},
  year = {2021},
  doi = {10.18653/v1/2021.eacl-main.204},
  eprint = {2006.09336},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.18653/v1/2021.eacl-main.204}
}

References

52 references, 13 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Wasi Uddin Ahmad, Zhisong Zhang, Xuezhe Ma, Eduard H. Hovy, Kai-Wei Chang, and Nanyun Peng. 2018. Near or far, wide range zero-shot cross-lingual dependency parsing. CoRR, abs/1811.00570. find
  2. Waleed Ammar, George Mulcaire, Miguel Ballesteros, Chris Dyer, and Noah A. Smith. 2016. Many languages, one parser. Transactions of the Association for Computational Linguistics, 4:431–444. find our card
  3. Johannes Bjerva, Robert Östling, Maria Han Veiga, Jörg Tiedemann, and Isabelle Augenstein. 2019. What do language representations really represent? Computational Linguistics, 45(2):381–389. find
  4. Christopher J. Burges, Robert Ragno, and Quoc V. Le. 2007. Learning to rank with nonsmooth cost functions. In B. Schölkopf, J. C. Platt, and T. Hoffman, editors, Advances in Neural Information Processing Systems 19, pages 193–200. MIT Press. find
  5. Rafael Monroy Casas and JM Hernández Campoy. 1995. A sociolinguistic approach to the study of idioms: Some anthropolinguistic sketches. Cuader-nos de Filologı́a inglesa, 4. find
  6. Yo Joong Choe, Kyubyong Park, and Dongwoo Kim. 2020. word2word: A collection of bilingual lexicons for 3,564 language pairs. In Proceedings of the 12th International Conference on Language Resources and Evaluation (LREC 2020). find
  7. Alexis Conneau, German Kruszewski, Guillaume Lample, Loı̈c Barrault, and Marco Baroni. 2018. What you can cram into a single $&!\#* vector: Probing sentence embeddings for linguistic properties. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long… find our card
  8. Béatrice Daille. 1994. Approche mixte pour l’extraction automatique de terminologie: statistiques lexicales et filtres linguistiques. Ph.D. thesis, Ph. D. thesis, Université Paris 7. find
  9. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies,… find
  10. Timothy Dozat and Christopher D. Manning. 2016. Deep biaffine attention for neural dependency parsing. CoRR, abs/1611.01734. find our card
  11. Aparna Garimella, Rada Mihalcea, and James Pennebaker. 2016. Identifying cross-cultural differences in word usage. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 674– 683, Osaka, Japan. find
  12. The COLING 2016 Organizing Committee. find
  13. Dirk Goldhahn, Thomas Eckart, and Uwe Quasthoff. 2012. Building large monolingual dictionaries at the Leipzig Corpora Collection: From 100 to 200 languages. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12), pages 759–765, Istanbul, Turkey. European… find our card
  14. Edward Twitchell Hall. 1989. Beyond culture. Anchor. find
  15. Geert H Hofstede, Gert Jan Hofstede, and Michael Minkov. 2005. Cultures and organizations: Software of the mind, volume 2. Mcgraw-hill New York. find
  16. Joshua Conrad Jackson, Joseph Watts, Teague R. Henry, Johann-Mattis List, Robert Forkel, Peter J. Mucha, Simon J. Greenhill, Russell D. Gray, and Kristen A. Lindquist. 2019. Emotion semantics show both cultural variation and universal structure. Science, 366(6472):1517–1522. find
  17. Kalervo Järvelin and Jaana Kekäläinen. 2002. Cumulated gain-based evaluation of IR techniques. ACM Transactions on Information Systems (TOIS), 20(4):422–446. find
  18. Melvin Johnson, Mike Schuster, Quoc V. Le, Maxim Krikun, Yonghui Wu, Zhifeng Chen, Nikhil Thorat, Fernanda Viégas, Martin Wattenberg, Greg Corrado, Macduff Hughes, and Jeffrey Dean. 2017. Google’s multilingual neural machine translation system: Enabling zero-shot translation. Transactions of the As… find
  19. Jihen Karoui, Farah Benamara, Véronique Moriceau, Viviana Patti, Cristina Bosco, and Nathalie Aussenac-Gilles. 2017. Exploring the impact of pragmatic phenomena on irony detection in tweets: A multilingual corpus study. In Proceedings of the 15th Conference of the European Chapter of the Associatio… find our card
  20. Guolin Ke, Qi Meng, Thomas Finley, Taifeng Wang, Wei Chen, Weidong Ma, Qiwei Ye, and Tie-Yan Liu. 2017. Lightgbm: A highly efficient gradient boosting decision tree. In I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett, editors, Advances in Neural Information… find
  21. Zoltán Kövecses. 2003. Language, figurative thought, and cross-cultural comparison. Metaphor and Symbol, 18(4):311–320. find
  22. Zoltán Kövecses. 2010. Metaphor: A practical introduction. Oxford University Press. find
  23. Guillaume Lample and Alexis Conneau. 2019. Cross-lingual language model pretraining. Advances in Neural Information Processing Systems (NeurIPS). find
  24. Guillaume Lample, Alexis Conneau, Marc’Aurelio Ranzato, Ludovic Denoyer, and Hervé Jégou. 2018. Word translation without parallel data. In International Conference on Learning Representations. find
  25. Xin Li, Lidong Bing, Wenxuan Zhang, and Wai Lam. 2019. Exploiting BERT for end-to-end aspect-based sentiment analysis. In Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019), pages 34–41, Hong Kong, China. Association for Computational Linguistics. find
  26. Bill Yuchen Lin, Frank F. Xu, Kenny Zhu, and Seung-won Hwang. 2018. Mining cross-cultural differences and similarities in social media. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 709–719, Melbourne, Australia. Association… find
  27. Yu-Hsiang Lin, Chian-Yu Chen, Jean Lee, Zirui Li, Yuyan Zhang, Mengzhou Xia, Shruti Rijhwani, Junxian He, Zhisong Zhang, Xuezhe Ma, Antonios Anastasopoulos, Patrick Littell, and Graham Neubig. 2019. Choosing transfer languages for cross-lingual learning. In Proceedings of the 57th Annual Meeting of… find our card
  28. Patrick Littell, David R. Mortensen, Ke Lin, Katherine Kairis, Carlisle Turner, and Lori Levin. 2017. URIEL and lang2vec: Representing languages as typological, geographical, and phylogenetic vectors. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational… find our card
  29. Nelson F. Liu, Matt Gardner, Yonatan Belinkov, Matthew E. Peters, and Noah A. Smith. 2019. Linguistic knowledge and transferability of contextual representations. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Tech… find our card
  30. Chaitanya Malaviya, Graham Neubig, and Patrick Littell. 2017. Learning language representations for typology prediction. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2529–2535, Copenhagen, Denmark. Association for Computational Linguistics. find
  31. Korac-Kakabadse Nada, Kouzmin Alexander, Korac-Kakabadse Andrew, and Savery Lawson. 2001. Low-and high-context communication patterns: towards mapping cross-cultural encounters. Cross Cultural Management: An International Journal, 8(2):3–24. find
  32. Graham Neubig and Junjie Hu. 2018. Rapid adaptation of neural machine translation to new languages. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 875–880, Brussels, Belgium. Association for Computational Linguistics. find our card
  33. Dat Quoc Nguyen, Dai Quoc Nguyen, Dang Duc Pham, and Son Bao Pham. 2014. RDRPOSTagger: A ripple down rules-based part-of-speech tagger. In Proceedings of the Demonstrations at the 14th Conference of the European Chapter of the Association for Computational Linguistics, pages 17–20, Gothenburg, Swede… find
  34. Joakim Nivre, Mitchell Abrams, Željko Agić, and et al. 2018. Universal dependencies 2.2. LINDAT/CLARIAH-CZ digital library at the Institute of Formal and Applied Linguistics (ÚFAL), Faculty of Mathematics and Physics, Charles University. find
  35. Ulrike Oster. 2019. Cross-cultural semantic and prag-matlc profiling of emotion words. regulation and expression of anger in Spanish and German. Current Approaches to Metaphor Analysis in Discourse, 39:35. find
  36. Ye Qi, Devendra Sachan, Matthieu Felix, Sarguna Pad-manabhan, and Graham Neubig. 2018. When and why are pre-trained word embeddings useful for neural machine translation? In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langu… find our card
  37. Vinit Ravishankar, Memduh Gökırmak, Lilja Øvrelid, and Erik Velldal. 2019. Multilingual probing of deep pre-trained contextual encoders. In Proceedings of the First NLPL Workshop on Deep Learning for Natural Language Processing, pages 37– 47, Turku, Finland. Linköping University Electronic Press. find
  38. Brian Richards. 1987. Type/token ratios: What do they really tell us? Journal of child language, 14(2):201– 209. find
  39. Tal Schuster, Ori Ram, Regina Barzilay, and Amir Globerson. 2019. Cross-lingual alignment of contextual word embeddings, with applications to zero-shot dependency parsing. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Lang… find
  40. In Coling 2010: Posters, pages 1256–1264, Beijing, China. find
  41. Coling 2010 Organizing Committee. find
  42. Jelena Vulanović. 2014. Cultural markedness and strategies for translating idiomatic expressions in the epic poem “The Mountain Wreath” into English. Mediterranean Journal of Social Sciences, 5(13):210. find
  43. Xinyi Wang and Graham Neubig. 2019. Target conditioned sampling: Optimizing data selection for multilingual neural machine translation. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5823–5828, Florence, Italy. Association for Computational Linguist… find
  44. Shijie Wu and Mark Dredze. 2019. Beto, bentz, be-cas: The surprising cross-lingual effectiveness of BERT. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 833–844,… find
  45. Bernard J. Siegel. 1977. Encyclopedia of anthropology. David E. Hunter and Phillip Whitten, eds. New York. American Anthropologist, 79(2):452–454. find
  46. Hu Xu, Bing Liu, Lei Shu, and Philip Yu. 2019. BERT post-training for review reading comprehension and aspect-based sentiment analysis. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long an… find our card
  47. Laura Smith, Salvatore Giorgi, Rishi Solanki, Johannes Eichstaedt, H Andrew Schwartz, Muhammad Abdul-Mageed, Anneke Buffone, and Lyle Ungar. 2016. Does ‘well-being’translate on twitter? In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 2042–2047. find
  48. Barret Zoph, Deniz Yuret, Jonathan May, and Kevin Knight. 2016. Transfer learning for low-resource neural machine translation. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 1568–1575, Austin, Texas. Association for Computational Linguistics. find
  49. Chi Sun, Xipeng Qiu, Yige Xu, and Xuanjing Huang. 2019. How to fine-tune bert for text classification? In Chinese Computational Linguistics, pages 194– 206, Cham. Springer International Publishing. find our card
  50. Ian Tenney, Patrick Xia, Berlin Chen, Alex Wang, Adam Poliak, R. Thomas McCoy, Najoung Kim, Benjamin Van Durme, Samuel R. Bowman, Dipanjan Das, and Ellie Pavlick. 2019. What do you learn from context? probing for sentence structure in contextualized word representations. In 7th International Confere… find our card
  51. B. Thompson, S. Roberts, and G. Lupyan. 2018. Quantifying semantic similarity across languages. Proceedings of the 40th Annual Conference of the Cognitive Science Society (CogSci 2018). find
  52. Yulia Tsvetkov and Shuly Wintner. 2010. Extraction of multi-word expressions from small parallel corpora. find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/sun-2021-cross-cultural-similarity-features-cross/