Bridging Background Knowledge Gaps in Translation with Automatic Explicitation
HyoJung Han, Jordan L. Boyd-Graber, Marine Carpuat
Abstract
Translations help people understand content written in another language. However, even correct literal translations do not fulfill that goal when people lack the necessary background to understand them. Professional translators incorporate explicitations to explain the missing context by considering cultural differences between source and target audiences. Despite its potential to help users, NLP research on explicitation is limited because of the dearth of adequate evaluation methods. This work introduces techniques for automatically generating explicitations, motivated by WIKIEXPL 1 : a dataset that we collect from Wikipedia and annotate with human translators. The resulting explicitations are useful as they help answer questions more accurately in a multilingual question answering framework. Source … 🙂 "I kn Literal Transl 🤔 "Wh Translation w …brother of de Villepin … 😃 "Ah Source No 🙂 on Literal Trans 🤔 "W Translation Many are th their "J'accu accusing the 😃 "A Cur P 🙂 1 …frère de Dominique de Villepin… Source 2 La veille de Noël 1800, sachant qu'... 3 …ont écrit leur « J'accuse… ! ». 🤔Literal 1 …brother of Dominique de Villepin … Translation 2 The day before Christmas 1800, knowing that 3 …have written their "J'accuse…!". 😃with Explicitation 1 …brother of the former French Prime Minister Dominique de Villepin … 2 On Christmas Eve in 1800, amid the French Revolution, 3 have written their "J'accuse…!", a famous open letter by a French novelist accusing the government in response to a miscarriage of justice. New Suggestions -A Translat target language. French-speaking Minister. Flags re language. Explicitati knowledge by add while ``J'accuse...! speakers need to b powerful. Example of cultural explicitation in French-English. Translators compensate for background knowledge gaps with explicitation in the target language. Here, while underlined parts do not need to be introduced in the French-speaking world, English speakers may need additional information, as in the red colored text, to enhance their understanding. Flags represent national identity and its associated cultural milieu rather than language. 🙂 1 …frère de Dominique de Villepin… Source 2 La veille de Noël 1800, sachant qu'... 3 …SNCF, en 2010… 🤔Literal 1 …brother of Dominique de Villepin … Translation 2 The day before Christmas 1800, knowing that 3 …SNCF, in 2010… 😃with Explicitation 1 …brother of the former French Prime Minister Dominique de Villepin … 2 On Christmas Eve in 1800, amid the French Revolution, 3 …railway authority SNCF, in 2010… French-English Example of . Translators compensate for background knowledge gaps with explicitation in the target language. Here, while underlined parts do not need to be introduced in the French-speaking world, English speakers may need additional information, as in the red colored text, to enhance their understanding. Flags represent national identity and its associated cultural milieu rather than language. 🙂 1 …frère de Dominique de Villepin… Source 2 La veille de Noël 1800, sachant qu'...
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 365e713b-87ca-40ee-a03d-5048d30029b0Cited by top-tier papers4
- An Interdisciplinary Approach to Human-Centered Machine TranslationMarine Carpuat, Omri Asscher, Kalika Bali, Luisa Bentivogli et al.EMNLP 2025 · 2 citations
- Toward Machine Interpreting: Lessons from Human Interpreting StudiesMatthias Sperber, Maureen de Seyssel, Jiajun Bao, Matthias PaulikEMNLP 2025 · 1 citation
- Liaozhai through the Looking-Glass: On Paratextual Explicitation of Culture-Bound Terms in Machine TranslationSherrie Shen, Weixuan Wang, Alexandra BirchEMNLP 2025
- You Make me Feel like a Natural Question: Training QA Systems on Transformed Trivia QuestionsTasnim Kabir, Yoo Yeon Sung, Saptarashmi Bandyopadhyay, Hao Zou et al.EMNLP 2024
Builds on4
- Elaborative Simplification as Implicit Questions Under DiscussionYating Wu, William Sheffield, Kyle Mahowald, Junyi Jessy LiEMNLP 2023 · 4 citations
- SimQA: Detecting Simultaneous MT Errors through Word-by-Word Question AnsweringHyoJung Han, Marine Carpuat, Jordan L. Boyd-GraberEMNLP 2022 · 3 citations
- Detecting Fine-Grained Cross-Lingual Semantic Divergences without Supervision by Learning to RankEleftheria Briakou, Marine CarpuatEMNLP 2020
- Challenges and Strategies in Cross-Cultural NLPDaniel Hershcovich, Stella Frank, Heather C. Lent, Miryam de Lhoneux et al.ACL 2022
Related papers
- Controlling Neural Machine Translation Formality with Synthetic SupervisionXing Niu, Marine CarpuatAAAI 2020 · 39 citations
- Crossing the Threshold: Idiomatic Machine Translation through Retrieval Augmentation and Loss WeightingEmmy Liu, Aditi Chaudhary, Graham NeubigEMNLP 2023 · 2 citations
- Explaining Relationships Between Scientific DocumentsKelvin Luu, Xinyi Wu, Rik Koncel-Kedziorski, Kyle Lo et al.ACL 2021
- Exploring the Efficacy of Automatically Generated Counterfactuals for Sentiment AnalysisLinyi Yang, Jiazheng Li, Padraig Cunningham, Yue Zhang et al.ACL 2021
- Synthetic Data Augmentation for Zero-Shot Cross-Lingual Question AnsweringArij Riabi, Thomas Scialom, Rachel Keraron, Benoît Sagot et al.EMNLP 2021
