Elamur Research⌕
☰
home / papers / 2023 / Bridging Background Knowledge Gaps in Translation with Automatic Explicitation

Bridging Background Knowledge Gaps in Translation with Automatic Explicitation

Summary

Translations that are accurate word for word can still leave readers confused when the source text assumes cultural knowledge they don't have. Human translators handle this with pragmatic explicitation: they add short clarifications, such as describing Dominique de Villepin as a former French Prime Minister. NLP has done little with this technique because labeled data and suitable evaluation methods are scarce.

The authors build WikiExpl, a corpus of naturally occurring explicitations. They mine noisy Wikipedia bitext (WikiMatrix) for unaligned target-side segments located next to named entities. They then use Wikidata properties to estimate whether each entity is closely tied to the source culture. Human translators annotate the resulting candidates.

Using what they learn from this data, the authors build a system that decides when an entity needs explanation and generates a brief description from Wikidata and the Wikipedia API. To evaluate usefulness, they check whether the added explanations help a multilingual question answering system. The generated explicitations do improve QA accuracy, which suggests that translation could serve cross-cultural users better by going beyond literal equivalence.

Key points

  • Resource: WikiExpl is built from WikiMatrix bitext with human-annotated explicitations. Examples cover French-English, and Polish entities are also mentioned. The dataset is released at github.com/h-j-han/automatic_explicitation.
  • Rarity: Explicitation is very rare in MT training data, appearing in only about 0.3% of the corpus. Even so, the collected examples were enough to develop a working system.
  • Detection rests on three assumptions: explicitations appear in unaligned spans, they occur near named entities, and they are more likely for culturally distant entities. Distance is measured through shifts in Wikidata properties across languages.
  • Evaluation: Usefulness is measured extrinsically through multilingual QA, and a short added phrase is often enough. The provided excerpt omits the exact accuracy figures.
  • Limitations:
    • Experiments cover only translation into English.
    • The method handles only named entities, so it misses cases like the year 1800.
    • Generation can be overly verbose (e.g., "Augustów, Sejny, Poland") or rely on terms that themselves need explaining (e.g., Zola and the Dreyfus affair for "J'accuse...!").
    • Annotators were paid USD 0.25 per example.

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

Topics: Named entity recognition

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2023.emnlp-main.603 · arXiv 2312.01308

@inproceedings{han2023bridging,
  title = {{Bridging Background Knowledge Gaps in Translation with Automatic Explicitation}},
  author = {Han, HyoJung and Boyd-Graber, Jordan and Carpuat, Marine},
  booktitle = {Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing},
  year = {2023},
  doi = {10.18653/v1/2023.emnlp-main.603},
  eprint = {2312.01308},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.18653/v1/2023.emnlp-main.603}
}

References

55 references, 2 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Sunipa Dev, Vinodkumar Prabhakaran, David Adelani, Dirk Hovy, and Luciana Benotti, editors. 2023. Proceedings of the First Workshop on Cross-Cultural Considerations in NLP (C3NLP). Association for Computational Linguistics, Dubrovnik, Croatia. find
  2. Othman Ahmad Ali Abualadas. 2015. A linguistically-oriented approach to literary translation: A comparative pragmatic study of three arabic renditions of the english novel “wuthering heights”. find
  3. Aus Adil Abdulwahab. 2012. Necessities of pragmatic explicitation in translating english short stories into arabic. Adab AL Rafidayn, 42(61):1–34. find
  4. M. Baker. 1996. Corpus-based Translation Studies: The Challenges that Lie Ahead, Benjamins Translation Library, pages 175–188. John Benjamins Publishing Company, Netherlands. find
  5. Nicole Baumgarten, Bernd Meyer, and Demet Özçetin. 2008. Explicitness in translation and interpreting: A critical review and some empirical evidence (of an elusive concept). Across Languages and Cultures, 9(2):177–203. find
  6. Viktor Becher. 2010. Towards a more rigorous treatment of the explicitation hypothesis in translation studies. Trans-kom, 3(1):1–25. find
  7. B.E. Dimitrova. 2005. Expertise and Explicitation in the Translation Process. Benjamins translation library: EST subseries. John Benjamins Publishing Company. find
  8. Zi-Yi Dou and Graham Neubig. 2021. Word alignment by fine-tuning embeddings on parallel corpora. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 2112–2128, Online. Association for Computational Linguistics. find
  9. Ahmed Elgohary, Denis Peskov, and Jordan Boyd-Graber. 2019. Can you unpack that? learning to rewrite questions-in-context. 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… find
  10. Shoshana Blum-Kulka. 1986. Shifts of cohesion and coherence in translation. The Translation Studies Reader. London/New York: Routledge, pages 209– 305. find
  11. Shi Feng and Jordan Boyd-Graber. 2019. What AI can do for me: Evaluating machine learning interpretations in cooperative play. In International Conference on Intelligent User Interfaces. find
  12. Jordan Boyd-Graber, Brianna Satinoff, He He, and Hal Daumé III. 2012. Besting the quiz master: Crowdsourcing incremental classification games. In Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, pages 1290–1301,… find
  13. Ewa Gumul et al. 2017. Explicitation in simultaneous interpreting. A study into explicitating behaviour of trainee interpreters. Wydawnictwo Uniwersytetu Śl askiego. find
  14. Scott A Hale. 2014. Multilinguals and wikipedia editing. In Proceedings of the 2014 ACM conference on Web science, pages 99–108. find
  15. HyoJung Han, Marine Carpuat, and Jordan Boyd-Graber. 2022. SimQA: Detecting simultaneous MT errors through word-by-word question answering. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 5598–5616, Abu Dhabi, United Arab Emirates. Association for Com… find
  16. Brent Hecht and Darren Gergle. 2010. The tower of babel meets web 2.0: user-generated content and its applications in a multilingual context. In Proceedings of the SIGCHI conference on human factors in computing systems, pages 291–300. find
  17. Daniel Hershcovich, Stella Frank, Heather Lent, Miryam de Lhoneux, Mostafa Abdou, Stephanie Brandl, Emanuele Bugliarello, Laura Cabello Pi-queras, Ilias Chalkidis, Ruixiang Cui, Constanza Fierro, Katerina Margatina, Phillip Rust, and Anders Søgaard. 2022. Challenges and strategies in cross-cultural… find our card
  18. Jet Hoek, Jacqueline Evers-Vermeul, and Ted J.M. Sanders. 2015. The role of expectedness in the im-plicitation and explicitation of discourse relations. In Proceedings of the Second Workshop on Discourse in Machine Translation, pages 41–46, Lisbon, Portugal. Association for Computational Linguistics… find
  19. Shonosuke Ishiwatari, Hiroaki Hayashi, Naoki Yoshi-naga, Graham Neubig, Shoetsu Sato, Masashi Toy-oda, and Masaru Kitsuregawa. 2019. Learning to describe unknown phrases with local and global contexts. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computa… find
  20. Masoud Jalili Sabet, Philipp Dufter, François Yvon, and Hinrich Schütze. 2020. SimAlign: High quality word alignments without parallel training data using static and contextualized embeddings. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 1627–1643, Online. Associat… find
  21. Machine Translation, pages 495–506, Online. Association for Computational Linguistics. find
  22. Ralph Krüger. 2020. Explicitation in neural machine translation. Across Languages and Cultures, 21(2):195 – 216. find
  23. Ekaterina Lapshinova-Koltunski, Cristina España-Bonet, and Josef van Genabith. 2019. Analysing coreference in transformer outputs. In Proceedings of the Fourth Workshop on Discourse in Machine Translation (DiscoMT 2019), pages 1–12, Hong Kong, China. Association for Computational Linguistics. find
  24. Ekaterina Lapshinova-Koltunski and Christian Hardmeier. 2017. Discovery of discourse-related language contrasts through alignment discrepancies in English-German translation. In Proceedings of the Third Workshop on Discourse in Machine Translation, pages 73–81, Copenhagen, Denmark. Association for C… find
  25. Ekaterina Lapshinova-Koltunski, Marie-Pauline Krielke, and Christian Hardmeier. 2020. Coreference strategies in English-German translation. In Proceedings of the Third Workshop on Computational Models of Reference, Anaphora and Coreference, pages 139–153, Barcelona, Spain (online). Association for C… find
  26. Ekaterina Lapshinova-Koltunski, Heike Przybyl, and Yuri Bizzoni. 2021. Tracing variation in discourse connectives in translation and interpreting through neural semantic spaces. In Proceedings of the 2nd Workshop on Computational Approaches to Discourse, pages 134–142, Punta Cana, Dominican Republic… find
  27. Renhan Lou and Jan Niehues. 2023. Audience-specific explanations for machine translation. find
  28. Paolo Massa and Federico Scrinzi. 2012. Manypedia: Comparing language points of view of wikipedia communities. In Proceedings of the Eighth Annual International Symposium on Wikis and Open Collaboration, pages 1–9. find
  29. E.A. Nida. 1964. Toward a Science of Translating: With Special Reference to Principles and Procedures Involved in Bible Translating. E.J. Brill. find
  30. Kinga Klaudy. 1993. On explicitation hypothesis. Dániel Berzsenyi College. find
  31. E.A. Nida and C.R. Taber. 1969. The theory and practice of translation. Helps for translators, v. 8. United Bible Societes. find
  32. Kinga Klaudy. 1996. Back-translation as a tool for detecting explicitation strategies in translation. find
  33. E.A. Nida and C.R. Taber. 2003. The Theory and Practice of Translation. Helps for translators. Brill. find
  34. Kinga Klaudy. 1998. Explicitation. Routledge encyclopedia of translation studies, pages 80–84. find
  35. Anthony Pym. 2005. Explaining explicitation. New trends in translation studies. In honour of Kinga Klaudy, pages 29–34. find
  36. Mateusz Krubiński, Erfan Ghadery, Marie-Francine Moens, and Pavel Pecina. 2021. Just ask! evaluating machine translation by asking and answering questions. In Proceedings of the Sixth Conference on Sudha Rao and Hal Daumé III. 2018. Learning to ask good questions: Ranking clarification questions us… find
  37. Sudha Rao and Hal Daumé III. 2019. Answer-based Adversarial Training for Generating Clarification Questions. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 143–… find
  38. Pedro Rodriguez, Shi Feng, Mohit Iyyer, He He, and Jordan L. Boyd-Graber. 2019. Quizbowl: The case for incremental question answering. CoRR, abs/1904.04792. — [arXiv:1904.04792](https://arxiv.org/abs/1904.04792) find
  39. Gabriela Saldanha. 2008. Explicitation revisited:: Bringing the reader into the picture. Trans-kom, 1(1):20–35. find
  40. Holger Schwenk, Vishrav Chaudhary, Shuo Sun, Hongyu Gong, and Francisco Guzmán. 2021. Wiki-Matrix: Mining 135M parallel sentences in 1620 language pairs from Wikipedia. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages… find
  41. Candace Séguinot. 1988. Pragmatics and the explicitation hypothesis. TTR: traduction, terminologie, rédaction, 1(2):106–114. find
  42. M. Snell-Hornby. 2006. The Turns of Translation Studies: New paradigms or shifting viewpoints? Benjamins Translation Library. John Benjamins Publishing Company. find
  43. Mary Snell-Hornby. 1990. Linguistic transcoding or cultural transfer? a critique of translation theory in germany. Translation, history and culture, 82. find
  44. Neha Srikanth and Junyi Jessy Li. 2021. Elaborative simplification: Content addition and explanation generation in text simplification. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 5123–5137, Online. Association for Computational Linguistics. find
  45. Simone Tedeschi, Valentino Maiorca, Niccolò Campolungo, Francesco Cecconi, and Roberto Navigli. 2021. WikiNEuRal: Combined neural and knowledge-based silver data creation for multilingual NER. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 2521–2533, Punta Cana, Domi… find
  46. Masaru Tomita, Masako Shirai, Junya Tsutsumi, Miki Matsumura, and Yuki. 1993. Evaluation of MT systems by TOEFL. In Proceedings of the Fifth Conference on Theoretical and Methodological Issues in Machine Translation of Natural Languages, Kyoto, Japan. find
  47. Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, Aurelien Rodriguez, Armand Joulin, Edouard Grave, and Guillaume Lample. 2023. Llama: Open and efficient foundation language models. arXiv pr… find
  48. Jean-Paul Vinay and Jean Darbelnet. 1958. Stylistique Comparee Du Francais Et De L’anglais. Biblio-theque de stylistique comparee. Paris: Didier. find
  49. Jean-Paul Vinay and Jean Darbelnet. 1995. Comparative Stylistics of French and English: A Methodology for Translation, volume 11 of Benjamins translation library. John Benjamins Publishing Company. find
  50. Yogarshi Vyas, Xing Niu, and Marine Carpuat. 2018. Identifying semantic divergences in parallel text without annotations. 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 1… find
  51. Bonnie Webber, Marine Carpuat, Andrei Popescu-Belis, and Christian Hardmeier, editors. 2015. Proceedings of the Second Workshop on Discourse in Machine Translation. Association for Computational Linguistics, Lisbon, Portugal. find
  52. Yating Wu, William Sheffield, Kyle Mahowald, and Junyi Jessy Li. 2023. Elaborative simplification as implicit questions under discussion. find our card
  53. Binwei Yao, Ming Jiang, Diyi Yang, and Junjie Hu. 2023. Empowering llm-based machine translation with cultural awareness. find
  54. Linn Øverås. 1998. In search of the third code: An investigation of norms in literary translation. Meta, 43(4):557–570. find
  55. Algorithm 1: Detecting explicitation span in bitext Input: Sentence pair (X src , X tgt ), E = {e\|named entity e in X} Output: Candidate C with unaligned segment u and its related entity e 1 U = unaligned_segments tgt (X src , X tgt ) 2 R = {(e, u)\|is_near_and_related(e, u), e ∈ E, u ∈ U } 3 C = {(e… find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/han-2023-bridging-background-knowledge-gaps-translation/