British Library Labs - Overview Talk 2017
- 1. Context and collections, and the British Library Ben O’Steen, British Library Labs @benosteen
- 3. The British Library Inside the British Library Space for 1200 readers, around 400,000 visitors per year Uses low oxygen and robots Reading room and delivery to London Document Supply and Storage at Boston Spa Stockton-on-Tees Author right to payment each time their books are borrowed from public libraries. St Pancras, London, UK Many books are stored 4 stories below the building Legal Deposit Library – Reference only
- 4. Living Knowledge Vision (2015 – 2023) Custodianship Research Business Culture Learning International Document:http://goo.gl/h41wW7 Speech:https://goo.gl/Py9uHK Roly Keating (Chief Executive Officer of the British Library) To make our intellectual heritage accessible to everyone, for research, inspiration and enjoyment and be the most open, creative and innovative institution of its kind by 2023.
- 5. Collections – not just books! > 180*million items > 0.8* m serial titles > 8* m stamps > 14* m books > 3* m sound recordings > 4* m maps > 1.6* m musical scores > 0.3* m manuscripts > 60* m patents King’s Library *Estimates
- 6. Wider…not just Researchers Researchers https://goo.gl/WutNyi Artists http://goo.gl/nNKhQ2 Librarians Curators https://goo.gl/9NWZUW Software Developers https://goo.gl/7QQ5Tf Archivists https://goo.gl/x7b4tg Educators https://goo.gl/qh01Mi
- 11. Digital research methods Visualisations Application Programming Interfaces for datasets e.g. Metadata, Images Annotation Location based searching & Geo-tagging Crowdsourcing Human Computation
- 12. How did we do this?
- 13. Competitions Awards Projects Tell us your ideas of what to do with our digital content Show us what you have already done with our digital content in research, artistic, commercial and learning and teaching categories Talk to us about working on collaborative projects
- 14. Getting to the heart of it British Library Labs works with researchers on their specific problems, trying to assess how widely this problem is felt. With their help, we talk to communities of researchers and try to pinpoint what they need as opposed to what they think they need to ask us.
- 15. Researchers often ask for all the content we have. What does that mean for digitised items in practice?
- 16. Taking a peek at our Open Data A digitised book…
- 17. 002819694
- 20. OCR XML Generated by ABBY Fine Reader
- 21. Could Labs provide other ways to understand this book?
- 24. Optically Character Recognised (OCR) generated Text Scanned Page Image on Flickr Commons https://goo.gl/AC43vs
- 28. Iterative crowdsourcing? (The term is borrowed from Mia Ridge.) 1. Crowdsource broad facts and subcollections of related items emerge. 2. No 'one-size-fits-all': Subcollections allow for more focussed curation. GOTO 1
- 31. SherlockNet: Competition Winner 2016 Karen Wang, Luda Zhao and Brian Do Using Convolutional Neural Networks to Automatically Tag and Caption the British Library Flickr Commons 1 million Image Collection 12 categories >20 million tags added >100,000 captions bit.ly/sherlocknet Pooled surrounding OCR text on page from similar images Used Microsoft COCO (photographs) & British Museum Prints and Drawings collections as training sets. Tags Captions
- 32. Artistic / Creative Works http://goo.gl/dM8ie A Mario Klingeman (2015) David Normal 2014 and 2015 Kris Hoffman (2016) https://goo.gl/Qilqq T Jiayi Chong 2016 Ling Low 2016 https://www.youtube.com/watch?v=bcOP1E5bRE0 https://www.facebook.com/RealmlandStory/ Paul Rand Pierce 2016 A Hat on the Ground Spells trouble Tragic Looking Women 44 Men who Look 44 (Notice the direction faces)
- 33. Imaginary Cities – BL Labs Project 16-17 Michael Takeo Magruder https://goo.gl/4ARwTy An artistic exploration seeking to create provocative fictional cityscapes for the Information Age from the British Library’s digital collection of historic urban maps
- 35. Mario Klingemann 2016 https://www.youtube.com/watch?v=xgnxnmqnR7Y Google Arts and Culture Lab – Experiments with Machine Learning https://artsexperiments.withgoogle.com/
- 38. Mario Klingemann
- 40. MIT Moral Machine survey: http://moralmachine.mit.edu/
- 46. Creative Uses • David Normal installation at Burning Man Festival • “Moments” by Joe Bell • Colouring-in Pages for Children
- 50. Burning Man Festival David Normal created light boxes around the Burning man, using the British Library’s Flickr Images
- 51. “Crossroads of Curiosity” (20th June -> November, 2015)
- 53. But how can anyone find anything useful?
- 54. John Cooper, https://www.flickr.com/photos/atomicshed/2436324958 CC-BY-NC-ND 2.0
- 56. Infancy of understanding Large-scale analysis of text is evolving but young. Exasperating situation where ‘black boxes’ of algorithms are used to draw conclusions. http://www.scottbot.net/HIAL/?p=41271
- 57. “Black Boxes”: a misnomer It is legitimate and useful to use code that you could not write. It is not legitimate to simply believe the ‘label’ on the side of the box. E.g. “Sentiment Analysis” is often nothing of the sort.
- 58. Quoting Scott Weingart: (emphasis mine) ● Do sentiment analysis algorithms agree with one another enough to be considered valid? ● Do sentiment analysis results agree with humans performing the same task enough to be considered valid? ● Is Jockers’ instantiation of aggregate sentiment analysis validly measuring anything besides random fluctuations? ● Is aggregate sentiment analysis, by human or machine, a valid method for revealing plot arcs? ● If aggregate sentiment analysis finds common but distinct patterns and they don’t seem to map onto plot arcs, can they still be valid measurements of anything at all? ● Can a subjective concept, whether measured by people or machines, actually be considered invalid or valid? (again from http://www.scottbot.net/HIAL/?p=41271)
- 62. Digitisation Often through Partnerships with Commercial & Other Organisations Bias in digitisation http://goo.gl/bR9UJ L Sample Generator
- 63. Open Licensed Digital Content? 15% Openly Licensed Around 10%* available online Working through Breakdown by collection* Manuscripts 59% Books 9% Maps and Views 7% Newspapers 3% Archives and Records 3% Paintings, Prints and Drawings 2% *Based on digitisation projects Largest proportion of funding Public / Private Partnership 15%* Openly Licensed 85%* Available onsite *Estimates
- 64. Accessing digital collections onsite OPEN £ •Have to be ‘onsite’ •Need to be security cleared for some collections – Hence ‘Researcher in Residence Model’ •Permission required (depending on ‘story’ of collection) •Content on various media formats •20 % re-use of material for non commercial research for some collections •We are learning ‘pathways’ so that this becomes ‘everyday’ to provide onsite access in the future
- 65. Typical pattern of research for Labs •Finding invisible things in ‘messy’ historical data •Unearthing / unlocking hidden histories and data to stimulate new research •Celebrating hidden histories / data creatively through events, art and performance
- 66. Finding things in messy OCR text Mrs Folly • Clean up some manually • Get human ‘ground truth’ • Write code to find things reliably in it automatically • Try code on messy content • Tweak if necessary • Digital ‘lasso’ around content • Human sift through Mrs Folly
- 67. Code: Machine Learning / Reading •Analogies to how humans read / learn •Machines acquire ‘knowledge’ / data and use that knowledge / data to make sense / identify patterns •Labs doing this on a case by case basis so methods can vary •Need computational AND human effort •Legalities of this process being ‘ironed’ out with publishers, •Often a misunderstood area… •Computers look for ‘patterns’ or the ‘essence’ of something
- 72. Katrina Navickas (2015) Political Meetings Mapper http://politicalmeetingsmapper.co .uk https://goo.gl/Qq78Oa Labs Symposium 2015 https://goo.gl/BSA3be Interview 2015 The Chartist Newspaper http://goo.gl/vOLSn H Chartist Monster Meeting Chartists Walking Tour and Re-enactment London
- 73. Working with Newspaper Collections Using Jupyter Notebooks
- 74. Virtual Infrastructure for OCR text OCR text scraped from digitised newspapers and in cloud Jupyter notebook Write python code and results in browser http://jupyter.org Access available for researchers ‘in residence’
- 75. Black Abolitionists In the UK Researcher: Hannah Rose Murray
- 76. Black Abolitionist Performances & their Presence in Britain (2016) – Hannah-Rose Murray Aberdeen Journal, 5 February 1851 “Fugitive Slaves” Aberdeen Journal, 14 April 1847 “Frederick Douglass, The Emancipated Slave” Frederick Douglass Ellen Craft Josiah Henson Ida B Wells A Performance by Joe Williams & Martelle Edinborough http://frederickdouglassinbritain.com/
- 78. Use of Overproof / OCR Correction? Re-OCR with ABBY FineReader? https://www.abbyy.com/en-gb/ http://overproof.projectcomputing.com/
- 80. Surveyed a set portion of the collection for words we were interested in, and those 1 and 2 ‘distant’ from these (Levenshtein distance).
- 83. Classifiers allowed us to prioritise on relevant articles without us reading them:
- 84. Data-mining verse in 18th Century newspapers BL Labs Project 16-17, Jennifer Batt https://goo.gl/5Akthd Slides courtesy Jennifer BattJennifer Batt @ the BL on World Poetry Day
- 85. What thoj' among ourrelves, with too much Heat, or t W: fweutimes.wongle, wvhen we Ihould debate, W – (A confequential Ill which Freedom drawvs, fl t A bad Efficf, but from a noble Caufe) t We can with univeifal Zcal advance, to To cutb the faithlefs Arrogancccof V rance. hi Dublin Journal 10-14 September, 1745 Slides courtesy Jennifer Batt
- 86. Verse: 81% lines begin with initial capital Prose: 52% lines begin with initial capital Westminster Journal 3 March 1745 Slides courtesy Jennifer Batt
- 90. In Summary: - Context about how an digitised image came to be and why it was scanned is both crucial to understand and sometimes crucial to hide. - aka Opening up large collections brings its own issues. - Presentation shapes perception. - Too much trust in black boxes algorithms, like search engines or social feed suggestions. - So little of our history is online that there is a natural bias. The gaps are being filled in with less credible sources. - It still might have happened even if you cannot google it, and vice versa!
- 91. ←