Museums' Use of Natural Language Processing
Written by Kate Maffey
How are museums translating their material?
Natural Language Processing is used by a variety of institutions, including the fine arts. For a review on its origins and use, read this article. Many museums are employing professional translation services. For instance, the Field Museum in Chicago uses a company called Multilingual Connections, and the Denver Botanical Gardens, South Florida Science Center, and the Metropolitan Museum of Art use a company called Eriksen Translation. That is, museums must pay for professional human translators in order to offer material in multiple languages. When the Children’s Discovery Museum of San Jose, in 2015, translated materials so that they could engage more with Latino visitors, they decided to exclusively use human translations rather than machine translation because they wanted to ensure that their materials were true to the “spirit of the words,” not just that it offered visitors the gist of the material.
While the examples provided are exclusive to the United States, it seems that European countries use a similar model of hiring professional translators – two contract bidding announcements by the Museum of the Quai Branly – Jacques Chirac and the Museum of Bastia in France demonstrate that human translation is still the industry standard in Europe as well.
A great illustration of the current state of machine translation as useful but not quite good enough comes in an announcement for a translation sprint. Europeana Pro is an organization funded by the European Union that is dedicated to preserving and promoting cultural heritage. In their 2020 invitation to join sprint to translate foundational documents into more languages, the organizers of the sprint instructed participants to use a number of machine translation tools only “as long as you review the resulting text.” This instruction underlines the themes explored by this article: machine translation is good, but not yet good enough for professional use without human review.
Figure 1: Black and white photos in a gallery. Source: Unsplash.
How will museums be affected when machine translation achieves parity with human translation?
Machine translation clearly is not yet good enough – but how could it change once the technology catches up to the need? User experience is naturally a priority for museums, and translation is an integral part of that. There are many museums in America that could better serve their non-English-speaking populations by expanding their offerings. And it is not just in serving their visitors; museums could also benefit greatly from better machine translation for their collections. A team of researchers from Beijing Jiaotong University used machine translation to evaluate ancient Chinese texts and translate them into English, demonstrating the promise of machine translation as a way to preserve and expand collection offerings. A research group based out of the University of California Los Angeles (UCLA) has a program dedicated to using automated translation to analyze and understand cuneiform languages on a series of tablets from southern Mesopotamia. A widely-used museum database software called Axiell has multilingual fields embedded in its data structures, and offers an automated translation tool so that curators have some idea of what they are looking at, even if it is in a language they do not understand.
Another team of researchers commented on translation in museums as a narrative and a means by which to convey identity. They explore how bad translation can be seen as a failure of the museum and argue that the quality of the translation not only has an impact on the museum, but also on the message that the museum wants to convey. A professor and researcher from the United Kingdom synthesized the benefits of translation for museums into two central themes: economic value and social inclusivity. However, given that a professional translation service is often required, that is currently not always an option for museums.
While professional translation services are the norm, some museums are starting to explore machine translation as a potential tool. The Computer History Museum conducted an experiment with artificial intelligence during which they used machine translation on a number of their audio and video files. While it is unclear if they have put it into effect so far, they underscored many of the points made in this article by commenting that machine translation promises to make museums and collections “more accessible to speakers of languages other than English.”
All of this evidence points to the potential disruption and change that could occur for museums when machine translation becomes a ubiquitous option for professional-level translation. Besides machine translation’s promise of museums’ ability to better serve communities in America, the international museum industry also thrives off the ability to offer people a window into culture and identity that isn’t possible without accurate translations. The significant reduction of costs that would occur if machine translation improved would offer museums the ability to broaden their offerings and expand their visitor experience beyond their current capabilities.
+ Resources
Axiell. n.d. “Axiell – Bringing Culture and Knowledge to Life.” Axiell. Accessed March 2, 2022a. https://www.axiell.com/.
Axiell. n.d. “Interface Functionality: Editing or Translating Adlib Interface Texts.” Accessed March 2, 2022b. http://documentation.axiell.com/alm/en/ds_tmeditingtranslatingtexts.html#autotranslate.
Axiell. n.d. “Translations Manager: Introduction.” Accessed March 2, 2022c. http://documentation.axiell.com/alm/en/ds_tmintroduction.html.
Bapna, Ankur, and Orhan Firat. 2019. “Exploring Massively Multilingual, Massive Neural Machine Translation.” Google AI Blog (blog). October 11, 2019. http://ai.googleblog.com/2019/10/exploring-massively-multilingual.html.
Chen, Chia-Li, and Min-Hsiu Liao. 2017. “National Identity, International Visitors: Narration and Translation of the Taipei 228 Memorial Museum.” Museum and Society 15 (1): 56–68. https://doi.org/10.29311/mas.v15i1.662.
“Cohere.” n.d. Cohere. Accessed March 2, 2022. https://cohere.ai.
David C. Brock. 2022. “A Museum’s Experience With AI.” CHM. February 3, 2022. https://computerhistory.org/blog/a-museums-experience-with-ai/.
Eriksen Translations Inc. 2019. “Museum Audience Engagement: Translation Strategies to Promote Diversity.” Eriksen Translations Inc. September 19, 2019. https://eriksen.com/arts-culture/museum-audience-engagement-translation-strategies/.
Eriksen Translations Inc. n.d. “Translating and Typesetting the Met Guides into 6 Languages.” Eriksen Translations Inc. Accessed March 2, 2022a. https://eriksen.com/work/met-guides/.
Eriksen Translations Inc. n.d. “Translating Exhibition Materials for the South Florida Science Center.” Eriksen Translations Inc. Accessed March 2, 2022b. https://eriksen.com/work/exhibition-displays/.
Eriksen Translations Inc. n.d. “Translating the Garden Tool Mobile Website for Denver Botanic Gardens.” Eriksen Translations Inc. Accessed March 2, 2022c. https://eriksen.com/work/garden-tool-mobile-website/.
Eriksen Translations Inc. n.d. “Translation & Localization Services NYC | Eriksen Translations.” Eriksen Translations Inc. Accessed March 2, 2022d. https://eriksen.com/.
“Forefront: Fine-Tune and Deploy GPT-J, GPT-13B, and GPT-NeoX.” n.d. Accessed March 2, 2022. https://www.forefront.ai/helloforefront.com/.
Field Museum. 2018. “About.” Text. Field Museum. May 14, 2018. https://www.fieldmuseum.org/about.
Furui, S., T. Kikuchi, Y. Shinnaka, and C. Hori. 2004. “Speech-to-Text and Speech-to-Speech Summarization of Spontaneous Speech.” IEEE Transactions on Speech and Audio Processing 12 (4): 401–8. https://doi.org/10.1109/TSA.2004.828699.
Goel, Aman. 2018. “How Does Siri Work? The Science Behind Siri.” Magoosh Data Science Blog (blog). February 3, 2018. https://magoosh.com/data-science/siri-work-science-behind-siri/.
Hirschberg, Julia, and Christopher D. Manning. 2015. “Advances in Natural Language Processing.” Science 349 (6245): 261–66. https://doi.org/10.1126/science.aaa8685.
IBM Cloud Education. 2021. “What Are Neural Networks?” August 3, 2021. https://www.ibm.com/cloud/learn/neural-networks.
Lalwani, Tarun, Shashank Bhalotia, Ashish Pal, Vasundhara Rathod, and Shreya Bisen. 2018. “Implementation of a Chatbot System Using AI and NLP.” SSRN Scholarly Paper ID 3531782. Rochester, NY: Social Science Research Network. https://doi.org/10.2139/ssrn.3531782.
Leahy, Connor. 2022. “Announcing GPT-NeoX-20B.” EleutherAI Blog. February 2, 2022. https://blog.eleuther.ai/announcing-20b/.
Liao, Min-Hsiu. 2018. “Museums and Creative Industries: The Contribution of Translation Studies.” January 2018. https://jostrans.org/issue29/art_liao.php.
Marshall, Christopher. 2020. “What Is Named Entity Recognition (NER) and How Can I Use It?” Super.AI (blog). June 2, 2020. https://medium.com/mysuperai/what-is-named-entity-recognition-ner-and-how-can-i-use-it-2b68cf6f545d.
Martin, Jenni, and Marilee Jennings. 2015. “Tomorrow’s Museum: Multilingual Audiences and the Learning Institution.” Museums & Social Issues 10 (1): 83–94. https://doi.org/10.1179/1559689314Z.00000000034.
Matas, Ariadna. 2020. “OpenGLAM Translation Sprint at Europeana 2020.” Europeana Pro. September 2020. https://pro.europeana.eu/event/openglam-translation-sprint-at-europeana-2020.
Melisa Palferro. 2018. “Different Approaches to Museum Translation.” #ucreatewetranslate (blog). March 8, 2018. https://www.ucreatewetranslate.com/different-approaches-museum-translation/.
Menon, Yasmin, and Will Lach. 2021. “Creating Accessibility in Museums with High Quality Translations.” Eriksen Translations Inc. November 19, 2021. https://eriksen.com/arts-culture/accessibility-museums-high-quality-translations/.
Mingyu, Lu, and Si Xianzhu. 2010. “Application of Machine Translation to Chinese-English Translation of Relic Texts in Museum.” In 2010 International Conference on Intelligent System Design and Engineering Application, 1:355–58. https://doi.org/10.1109/ISDEA.2010.4.
Mitkov, Ruslan. 2004. The Oxford Handbook of Computational Linguistics. OUP Oxford. https://books.google.com/books?hl=en&lr=&id=yl6AnaKtVAkC&oi=fnd&pg=PA219&dq=part+of+speech+tagging&ots=_VVi1buLDj&sig=y-3BFecOVtTtptCNFrS8Br-EFGE#v=onepage&q=part%20of%20speech%20tagging&f=false.
MTAAC Team. n.d. “Machine Translation and Automated Analysis of Cuneiform Languages.” Machine Translation and Automated Analysis of Cuneiform Languages. Accessed March 2, 2022. https://cdli-gh.github.io/mtaac/.
Multilingual Connections. n.d. “Museum Translation Services.” Multilingual Connections. Accessed March 2, 2022. https://multilingualconnections.com/industry-experience/museums-cultural-institutions/.
Nadeem, Moin, Anna Bethke, and Siva Reddy. 2020. “StereoSet: Measuring Stereotypical Bias in Pretrained Language Models.” ArXiv:2004.09456 [Cs], April. http://arxiv.org/abs/2004.09456.
Och, Franz. n.d. “Statistical Machine Translation Live.” Google AI Blog (blog). Accessed March 2, 2022. http://ai.googleblog.com/2006/04/statistical-machine-translation-live.html.
Papineni, Kishore, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. “Bleu: A Method for Automatic Evaluation of Machine Translation.” In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, 311–18. Philadelphia, Pennsylvania, USA: Association for Computational Linguistics. https://doi.org/10.3115/1073083.1073135.
Scott, Josh. 2022. “Cohere Closes $125 Million USD Series B Round Led by Tiger Global.” BetaKit (blog). February 15, 2022. https://betakit.com/cohere-closes-125-million-usd-series-b-round-led-by-tiger-global/.
Siddhant, Aditya, Melvin Johnson, Henry Tsai, Naveen Ari, Jason Riesa, Ankur Bapna, Orhan Firat, and Karthik Raman. 2020. “Evaluating the Cross-Lingual Effectiveness of Massively Multilingual Neural Machine Translation.” Proceedings of the AAAI Conference on Artificial Intelligence 34 (05): 8854–61. https://doi.org/10.1609/aaai.v34i05.6414.
Simonite, Tom. 2022. “YouTube’s Captions Insert Explicit Language in Kids’ Videos.” Wired, February 24, 2022. https://www.wired.com/story/youtubes-captions-insert-explicit-language-kids-videos/?utm_source=nl&utm_brand=wired&utm_mailing=WIR_FastForward_022822&utm_campaign=aud-dev&utm_medium=email&utm_content=WIR_FastForward_022822&bxid=60a682d211af1a6455755091&cndid=65158197&esrc=bouncexmulti_second%20&source=EDT_WIR_NEWSLETTER_0_TRANSPORTATION_ZZ&mbid=mbid%3DCRMWIR012019%0A%0A&utm_term=WIR_Transportation.
Turovsky, Barak. 2016a. “Ten Years of Google Translate.” Google. April 28, 2016. https://blog.google/products/translate/ten-years-of-google-translate/.
Turovsky, Barak. 2016b. “Found in Translation: More Accurate, Fluent Sentences in Google Translate.” Google. November 15, 2016. https://blog.google/products/translate/found-translation-more-accurate-fluent-sentences-google-translate/.
Zhu, Aihua. 2021. “Man-Machine Translation—Future of Computer-Assisted Translation.” Journal of Physics: Conference Series 1861 (1). http://dx.doi.org/10.1088/1742-6596/1861/1/012088.