All things must come to an end eventually – even the Europeana Newspapers project. The good news is that in every end, there is also a new beginning. But more on this later.

After 38 months of hard, but also very fun and rewarding work with our network, the project has officially come to a close in March 2015. But as usual with such endeavours, there are still many activities which go on beyond the lifetime of the project, such as reporting and reviewing, disseminating and spreading the results as well as fostering takeup and new initiatives around the use and exploitation of said outcomes.

And there are many valuable outcomes of the project – more than 20 million historic newspaper pages are now discoverable via Europeana, and close to 12 million pages are fully searchable in The European Library, thanks to the large-scale refinement work undertaken during the project. There are already some great examples of how this vast corpus can be utilised in research, or in the development of new services and applications. Nevertheless, with a collection of this size, the majority of it still needs to be explored and there are certainly many treasures buried within that yet remain to be discovered.

Europeana Newspapers has not only created a massive resource of easily accessible historical news, but also produced several handy tools for the exploitation and enrichement of digital newspapers, together with standards and best practices for collection holders that are aiming to provide their historical newspaper assets in similar ways.

Together, all these resources have really pushed the state-of-the-art of newspaper digitisation and presentation in Europe. And so here it comes: Europeana are already working on an exciting new development – a dedicated Europeana Newspaper channel will be launched in 2016! A new look and feel, more scalable servers, and possibly even more newspaper content are already in the pipeline. Make sure to follow us here and on social media to be amongst the first to hear about this.

Meanwhile, to encourage everyone to dive into all the rich resources delivered by Europeana Newspapers, we have summarised the main project results in a restyled special issue of our Final Report!

Prof. dr. Huub Wijfjes (RUG/UvA) showing word clouds used in his research.

On 24 March, we opened up our auditorium to 10 research projects that use our digitised newspapers. The presenters came from many areas of DH research as we had historians, linguists, computer programmers, a linked data specialist, and media researchers. Next to this, we also asked colleagues to present what they are working on with regards to our newspapers. This resulted in presentations about copyright, digitisation (OCR and future plans), a Wikipedia project, the Research Lab and Europeana Newspapers. All in all we had three blocks of presentations spanning the whole day, and an auditorium filled with interested researchers, journalists, librarians, students and colleagues.

The original idea of the day was to provide a networking opportunity for those researchers who used our newspapers in their projects, but while organising it we noticed that not only those researchers were interested in hearing what others are doing, but that a wider group of people wanted to know what was possible with the data set. When we opened up the registration, we quickly outgrew the room we booked and had to transfer to the auditorium. Ultimately, we had 145 people who visited the symposium and who were responsible for lively discussions after the presentations and during the breaks.

Discussions in between presentations.

The varied audience and speakers of the day also meant having different levels of expertise in Digital Humanities and working with data, but this provided very valuable insights into working with the newspapers. The differences in skills between, for example, a historian and a programmer provides challenges when working together in research projects, but also provides a very valuable learning experience for both.

Working with new computational methods might be a bit scary for an inexperienced researcher, but can mean very interesting results, according to Dr. Martijn Kleppe (EUR). But how does a researcher know if these results are trustworthy? If the software actually does its job? Dr. Antske Fokkens (VU) explains that it is important to show researchers that they should be aware of what software can and cannot do and how you should interpret results. Another common technical issue that researchers came across is the lack of computational capacity. Humanities faculties often do not have the setup to process large amounts of data.

Dr. Antske Fokkens on the methods used at the Vrije Universiteit.

Next to these technical challenges, the material itself also provides problems when using it, such as OCR issues, lack of access due to the copyright, changes in the meaning of words and historical spelling and of course the ‘problem’ that we have not yet digitised every newspaper page in our collection. Working with this data and around these challenges is something that we can work together in. The KB works hard to improve the access to and usability of the newspapers and with the KB Research Lab, we can also provide support in the use of the data.

Martijn Kleppe listening to his colleague Laura Hollink

Because of this, many researchers have already used the newspapers in great research projects, such as Polimedia. Here, our newspapers are linked to the parliamentary papers and the radio bulletins, providing a search engine that shows how parliamentary debates are mentioned in the media. Or the Dutch Ships and Sailors-project where maritime data is linked together (and to our newspapers) to provide information about Dutch ships in the 18th and 19th century. Mentioning all success stories might result in a very long blog, but all presentations (in Dutch) are available via our website (scroll down for the URLs).

We were very happy with the whole symposium, the great speakers and the wonderful audience and we hope to be able to organise something similar in the future. If you are interested in our newspapers, other data sets, or our Research Lab, feel free to contact us!

The Succeed project has recently been rated ‘Excellent ‘ by the European Commission. The final evaluation of the Succeed project took place on19th of February 2015, at the University of Alicante, during a meeting of the committee of experts appointed by the European Commission (EC) with the Succeed consortium members. The meeting was chaired by Cristina Maier, Succeed Project Officer from the European Commission.
Succeed has been funded by the European Union to promote the take up and validation of research results in mass digitisation, with a focus on textual content. For a description of the project and the consortium, see our earlier post Succeed project launched.

The outputs produced by Succeed during the project life span (January 2013-December 2014) are listed below.

Impact Interoperable Platform

Succeed further improved the Impact Interoperable Platform which allows users to test and combine a number of digitisation tools. The tools are made available as web services by a number of different providers, allowing the user to try them out online without having to install any of these tools locally. During the Succeed project, 20 new tools were integrated. The platform currently supports the online testing of 40 tools. Moreover, the option to execute workflows with the Taverna workflow Management System and MyExperiment has been added to the demonstration platform so that the user can define multistage processes (even processes involving input from multiple sub-processes) when several tools operate on the input. The interoperable platform has been integrated into the Impact Centre of Competence website to reinforce sustainability. The current version of the platform provides access to the open data-sets created by the Impact project – 250,000 high-resolution images and 30,000 ground truth files – with the recent addition of a specific viewer which allows the complete collection to be navigated.

Validation and take-up of tools

An overview with nearly 260 useful tools and resources for text digitisation has been compiled and published online. This online catalogue supports the filtering of tools and resources by their type and target language.

As part of the Succeed project, over 20 tools in this catalogue have been tested for validation and take-up in the productive environments of 13 libraries in several European countries. The National Library of the Netherlands also participated.

The tools included in this take-up programme supported a variety of workflows, including, among others, image processing and enhancement; image segmentation and layout analysis; text processing operations (i.e. named entity recognition); and evaluation of the output.

At the end of the project, 11 tools were successfully integrated into libraries’ productive environments. The National Library of the Netherlands implemented the Lexicon service which was developed by INL, the Institute for Dutch Lexicology, into the website Delpher. See also our previous blog post on Take-up of tools within the Succeed project.

Recommendations for digitisation projects

Succeed published two sets of recommendations for digitisation projects: the first one for metadata and data formats used in text digitisation and a second one for common licensing schemes for tools and resources.

The first report builds on existing recommendations and guidelines for metadata and data formats as well as ongoing initiatives. The analysis covers long-term preservation, online delivery, as well as advanced and supporting technologies.

The second report compiles existing licensing schemes and analyses their current usage by consulting a number of organisations, the inventory of tools for digitisation created by Succeed –containing more than 200 items–, and also popular software repositories such as SourceForge and GitHub.

Succeed events

The organisation of several events served to disseminate the latest technology for the digitisation of text. The events organized by Succeed are listed below.

• The Succeed Developers’ Workshops promoted the involvement of the community of programmers and developers in the further development of tools and services for digitisation. The First Developers’ Workshop took place at the National Library of the Netherlands on September 19-20, 2013. The Second Developers’ Workshop took place at the Universidad de Alicante on April 10-11, 2014.
• The Succeed tutorial State-of-the-art Tools for Text Digitisation was held in Valleta (Malta), September 22, 2013, in the framework of the TPDL 2013 conference. The tutorial aimed to present the latest technology for image enhancement, OCR, post-correction, logical structure analysis, lexicon building, deployment and enrichment. It gathered attendees from 15 cultural heritage institutions.
• The Succeed Workshop on interoperability of digitisation platforms took place at the National Library of the Netherlands (October 2, 2014). Nineteen researchers, librarians, and computer scientists from several European countries participated in the workshop.
• The Digitisation Days brought together 182 participants from complementary communities: researchers, companies and practitioners. The event took place on May 19-20, 2014 in Madrid. Also see our earlier blog post on this topic.
• The principal results of the project were presented at the Succeed final conference (November 28, 2014). The event took place in the Bibliothèque nationale de France, and brought together nearly 70 experts in the field of digitisation and cultural heritage. 

Succeed awards

Two editions of the Succeed awards have been organised with the objective of evaluating state-of-the-art technology, addressing particular stages of the digitisation workflow like segmentation and recognition.

The first Succeed awards distinguished the best initiatives in the application of advanced technology for the digitisation of historical texts. 18 submissions were judged by Succeed’s Expert Advisory Board. The following institutions were presented with awards during the Digitisation Days in Madrid:
• Hill Museum and Manuscript Library.
• Centre d’Études Supérieures de la Renaissance.
• Tecnilógica (Commendation of Merit).
• London Metropolitan Archives – University College London (Commendation of Merit).

The second edition recognised the best performance in the validation and take-up of digitisation tools promoted by Succeed. Among the 9 external participants, the following libraries received awards during Succeed’s final conference in Paris:
• Library of KU Leuven.
• National Library of Finland (Commendation of Merit).
• University Library of Wroclaw (Commendation of Merit).

Map of the European digitisation landscape

A map of the European digitisation landscape, compiling over 380 active projects, centres of competence, companies, public institutions and networks. An online search platform, developed by Succeed, allows for a highly usable access to the information therein. A registration gateway allows for personalised access and for maintenance of the information by the community.

Roadmap for sustainable centres of competence

A Roadmap for sustainable centres of competence to support digital libraries which provides insight into the capacity to support the evolution of European digital libraries through centres of competence. After investigating the main technical, capacity-related and economic challenges, some actions are proposed to advance the state-of-the-art as regards mass digitisation of cultural heritage in Europe in three respects: capacity building, advance of technology and sustainability.

Delpher

Delpher is a joint initiative of the Meertens Institute of Research and documentation of Dutch language and culture, the university libraries of Amsterdam (UvA), Groningen, Leiden and Utrecht, and the National Library of the Netherlands, to bring together the otherwise fragmented access to digitized historical text corpora.

Delpher currently contains over 90.000 books, over 1 million newspapers, containing more than 10 million pages, over 1.5 million pages from periodicals, and 1.5 million ANP news bulletins that are all full text searchable. New content will continually be added in the coming years.

Since the initial launch in November 2013 we received several suggestion for improvement or bug fixes. On the 20th of November 2014, exactly one year after the initial launch, a new version of Delpher was released. In the new version, the most important of these issues are solved. Delpher is now also mobile friendly, the overall user interaction is improved and the INL Lexicon Service was added.

The INL Lexicon Service

Delpher contains content ranging from the 17th until the 20th century. In this time period, the spelling of words has changed frequently. Doing a full text search in Delpher for the word koninklijke (royal) in the historical newspaper results in 1.207.342 newspaper articles, the oldest one dating back to 1674. During the mentioned time period, the word koninklijke had many spelling variants. A Delpher user who is unaware of these variants may miss out on many relevant resources. The importance of this issue was underlined by the ‘golden tip’ (in Dutch) provided by one of our users in the summer of 2014, i.e. to include a number of different spellings in search requests.

As part of the Succeed project, the Lexicon service as developed by INL, the Institute for Dutch Lexicology, was integrated in Delpher to tackle this problem. The INL LexiconService is a webservice that gives online access to the GiGaNT lexicon of 15th to 20th century Dutch by means of http requests.

Using the Lexicon Service, a user searching for “koninklijke” is now offered 14 spelling variants of “koninklijke”. After selecting one or more variants, the query is automatically expanded to an OR query including the selected variant(s). Searching for example for koninklijke or conincklicke or konincklijcke or koninglijk or koninglijke or keuninklijke or koningklyk gives 8.525 more results, the oldest one dating back to 1649. The implementation of the Lexicon Service in Delpher shows how it may be used in a library catalogue. For a complete overview of the possibilities of the webservice, please see the Succeed Wiki.

Try it out yourself!

The current version of Delpher has a Dutch interface only, but even without thorough knowledge of Dutch it’s probably not too hard to try out the new service. First activate the LexiconService in the settings screen: (“Zoeksuggesties tonen met historische spellingvarianten”). Then type your query in the advanced search fields (select “Uitgebreid zoeken”) and search for books, newspapers or periodicals.

Speaking the same language is one thing, understanding what the other is saying is another… – Carl Wilson at the Succeed technical workshop on the interoperability of digitisation platforms.

Interoperability is a term widely used to describe the ability of making systems and organisations work together (inter-operate). However, interoperability is not just about the technical requirements for information exchange. In a broader definition, it also includes social, political, and organisational factors that impact system to system performance and is related to questions of (commercial) power and market dominance (See http://en.wikipedia.org/wiki/Interoperability).

On 2 October 2014, the Succeed project organised a technical workshop on the interoperability of digitisation platforms at the National library of the Netherlands in The Hague. 19 researchers, librarians, and computer scientists from several European countries participated in the workshop (see SUCCEED Interoperability Workshop_Participants). In preparation of the workshop, the Succeed project team asked participants to fill out a questionnaire containing several questions on the topic of interoperability. The questionnaire was filled out by 12 participants; the results were presented during the workshop. The programme included a number of presentations and several interactive sessions to come to a shared view on what interoperability is about, what are the main issues and barriers to be dealt with, and how we should approach these.

The main goals of the workshop were:

1. Establishing a baseline for interoperability based on the questionnaire and presentations of the participants
2. Formulating a common statement on the value of interoperability
3. Defining the ideal situation with regard to interoperability
4. Identifying the most important barriers
5. Formulating an agenda

1. Baseline

Presentation by Carl Wilson

To establish a baseline (what is interoperability and what is its current status in relation to digitisation platforms), our programme included a number of presentations. We invited Carl Wilson of the Open Preservation Foundation (previously the Open Planets Foundation)  for the opening speech. He set the scene by sharing a number of historical examples (in IT and beyond) of interoperability issues. Carl made clear that interoperability in IT has many dimensions:

1. Technical dimensions
   Within the technical domain, two types of interoperability can be discerned, i.e.:
   Syntactical interoperability (aligning metadata formats); “speaking the same language”, and Semantical interoperability; “understanding each other
2. Organizational /Political dimensions
3. Legal (IPR) dimensions
4. Financial dimensions

When approaching operability issues, it might help to take into account these basic rules:

• Simplicity
• Standards
• Clarity
• Test early (automated testing, virtualisation)
• Test often

Finally, Carl stressed that the importance of interoperability will further increase with the rise of the Internet of Things, as it involves more frequent information exchange between more and more devices.

The Succeed Interoperability platform

After Carl Wilson’s introductory speech, Enrique Molla from the University of Alicante (UA is project leader of the Succeed project) presented the Succeed Interoperability framework, which allows users to test and combine a number of digitisation tools. The tools are made available as web services by a number of different providers, which allows the user to try them out online without having to install any of these tools locally. The Succeed project met with a number of interoperability related issues when developing the platform. For instance, the web services have a number of different suppliers; some of them are not maintaining their services. Moreover, the providers of the web services often have commercial interests, which means that they impose limits such as a maximum number of users of pages tested through the tools.

Presentations by participants

After the demonstration of the Succeed Interoperability platform, the floor was open for the other participants, many of whom had prepared a presentation about their own project and their experience with issues of interoperability.

Bert Lemmens presented the first results of the Preforma Pre-Commercial Procurement project (running January 2014 to December 2017). A survey performed by the project made clear that (technically) open formats are in many cases not the same as libre/ open source formats. Moreover, even when standard formats are used across different projects, they are often implemented in multiple ways. And finally, when a project or institution has found their technically appropriate format, they may often find that limited support is available on how to adopt the format.

Gustavo Candela Romero gave an overview of the services provided by the Biblioteca Virtual Miguel de Cervantes (BVMC) The BVMC developed their service oriented architecture with the purpose of facilitating online access to Hispanic Culture. The BVMC offers their data as OAI-PMH, allowing other institutions or researchers to harvest their content. Moreover, the BVMC is working towards publishing their resources in RDF and making it available through a SPARQL Endpoint.

Alastair Dunning and Pavel Kats explained how Europeana and The European Library are working towards a shared storage system for aggregators with shared tools for the ingestion and mapping process. This will have practical and financial benefits, as shared tools will reduce workflow complexity, are easier to sustain and, finally, cheaper.

Clara Martínez Cantón presented the work of the Digital Humanities Innovation Lab (LINHD), the research centre on Digital Humanities at the National Distance Education University (UNED) in Spain. The LINHD encourages researchers to make use of Linked Data. Clara showed the advantages of using Linked Data in a number of research projects related to metrical repertoires. In these projects, a number of interoperability issues (such as a variety of structures of the data, different systems used, and variation in the levels of access) were by-passed by making use of a Linked Data Model.

Marc Kemps-Snijders made clear how the Meertens Institute strives to make collections and technological advances available to the research community and the general public by providing technical support and developing applications. Moreover, the Meertens Institute is involved in a number of projects related to interoperability, such as Nederlab and CLARIN.

Menzo Windhouwer further elaborated on the projects deployed by CLARIN (Common Language Resources and Technology Infrastructure). CLARIN is a European collaborative effort to create, coordinate and make language resources and technology available and readily useable. CLARIN is involved in setting technical standards and creating recommendations for specific topics. CLARIN has initiated the Component MetaData Infrastructure (CMDI), which is an integrated semantic layer to
achieve semantic interoperability and overcome the differences between different metadata structures.

Presentation of responses to the Succeed questionnaire and overview of issues mentioned

To wrap up the first part of the programme, and to present an overview of the experiences and issues described by the participants, Rafael Carrasco from the University of Alicante presented the results of the Succeed online questionnaire (see also below).

Most institutions which filled out the questionnaire made clear that they are already addressing interoperability issues. They are mainly focusing on technical aspects, such as the normalization of resources or data and the creation of an interoperable architecture and interface. The motives for striving for interoperability were threefold: there is a clear demand by users; interoperability means an improved quality of service; and interoperability through cooperation with partner institutions brings many benefits to the institutions themselves. The most important benefits mentioned were: to create a single point of access (i.e., a better service to users), and to reduce the cost of software maintenance.

Tomasz Parkola and Sieta Neuerburg proceeded by recapturing the issues presented in the presentations. Clearly, all issues mentioned by participants could be placed in one of the dimensions introduced by Carl Wilson, i.e. Technical, Organizational/ Political, Financial, or Legal.

2. What is the value of interoperability?

Having established our baseline of the current status of interoperability, the afternoon programme of the workshop further included a number of interactive sessions, which were led by Irene Haslinger of the National library of the Netherlands. To start off, we asked the participants to write down their notion of the value of interoperability.

The following topics were brought up:

• Increased synergy
• More efficient/ effective allocation of resources
• Cost reduction
• Improved usability
• Improved data accessibility

3. How would you define the ideal situation with regard to interoperability?

After defining the value of interoperability, the participants were asked to describe their ‘ideal situation’.

The participants mainly mentioned their technical ideals, such as:

• Real time/ reliable access to data providers
• Incentives for data publishing for researchers
• Improved (meta)data quality
• Use of standards
• Ideal data model and/ or flexibility in data models
• Only one exchange protocol
• Automated transformation mechanism
• Unlimited computing capacity
• All tools are “plug and play” and as simple as possible
• Visualization analysis

Furthermore, a number of organizational ideals was brought up:

• The right skills reside in the right place/ with the right people
• Brokers (machines & humans) help to achieve interoperability

4. Identifying existing barriers

After describing the ‘ideal world’, we asked the participants to go back to reality and identify the most important barriers which – in their view – stop us from achieving the interoperability ideals described above.

In his presentation of the responses to the questionnaire, Rafael Carrasco had already identified the four issues considered to be the most important barriers for the implementation of interoperability:

• Insufficient expertise by users
• Insufficient documentation
• The need to maintain and/ or adapt third party software or webservices
• Cost of implementation

The following barriers were added by the participants:

Technical issues (in order of relevance)

• Pace of technological developments/ evolution
• Legacy systems
• Persistence; permanent access to data
• Stabilizing standards

Organizational/ Political issues (in order of relevance)

• Communication and knowledge management
• Lack of 21st century skills
• No willingness to share knowledge
• “Not invented here”-syndrome
• Establishment of trust
• Bridging the innovation gap; responsibility as well as robustness of tools
• Conflicts of interest between all stakeholders (e.g. different standards)
• Decision making/ prioritizing
• Current (EU) funding system hinders interoperability rather than helping it (funding should support interoperability between rather than within projects)

Financial issues (in order of relevance)

• Return of investment
• Resources
• Time
• Commercial interests often go against interoperability

Legal issues

• Issues related to Intellectual Property Rights

5. Formulate an agenda: Who should address these issues?

Having identified the most important issues and barriers, we concluded the workshop by an open discussion centering on the question: who should address these issues?

In the responses to the questionnaire, the participants had identified three main groups:

• Standardization bodies
• The research community
• Software developers

During the discussion, the participants added some more concrete examples;

• Centres of Competence established by the European Commission should facilitate standardization bodies by both influence the agenda (facilitate resources) and by helping institutions to find the right experts for the interoperability issues (and vice versa)
• Governmental institutions, including universities and other educational institutions, should strive to improve education in “21st century skills”, to improve users’ understanding of technical issues

At the end of our workshop, we concluded that, to achieve a real impact on the implementation of interoperability, there needs to be a demand from the side of the users, while the institutions and software developers need to be facilitated both organizationally and financially. Most probably, European centres of competence, such as Impact, have a role to play in this field. This is also most relevant in relation to the Succeed project. One of the project deliverables will be a Roadmap for funding Centres of Competence in work programmes. The role of Centres of Competences in relation to interoperability is one of the topics discussed in this document. As such, the results of the Succeed workshop on interoperability will be used as input for this roadmap.

We would like to thank all participants for their contribution during the workshop and look forward to working with you on interoperability issues in the future!

More pictures on Flickr

For the National Library, being a collection holder, the Succeed awards ceremony was one of the highlights of the conference, because it showed the application of technology to actual collections. The Succeed awards aim to recognise successful digitisation programmes in the field of historical texts, especially those using the latest technology.

Two prizes went to the Hill Museum and Manuscript Library and the Centre d’Études Supérieures de la Renaissance, while two Commendations of Merit were awarded to the London Metropolitan Archives/ University College London  and to Tecnilógica.

In her role of member of the IMPACT CoC executive board, the KB’s Head of Research, Hildelies Balk, took part in the ceremony and awarded the Commendation of Merit to the London Metropolitan Archives/ University College London for their Great Parchment Book project. You will find a short video about the project here.[youtube=http://www.youtube.com/watch?v=WDD2cVT7PeU]

Moreover, the KB hosted an interesting and fruitful Round table workshop on the future of research and funding in digitisation and the possible roles of Centres of Competence on 20 May. Some 30 librarians and researchers joined this workshop, and discussed the below topics:

• What research is needed to further the development of the Digital Library?
• How can Centres of Competence assist your research or development?
• In digitisation, are we ready to move the focus from quantity to quality?
• What enrichments, e.g. in Named Entity Recognition, Linked Data services, or crowdsourcing for OCR correction, would be most beneficial for digitisation?
• What’s your take on Labs and Virtual Research Environments?
• What would you like to do in these types of research settings?
• What do you expect to get out of them?

The preliminary outcomes of the workshop show that the main goal for institutions is to give users unrestricted access to data. During the workshop, the participants discussed the many layered aspects of these three topics, i.e. ‘users’, ‘access’, and ‘data’. Moreover, the participants gave their view on the following questions in relation to these topics:

• What stops us from making progress?
• What helps us to make progress?
• And what role could CoCs play in this?

The outcomes of the workshop have been documented and will be used as a starting point for the roadmap to further development of digitisation and the digital library, which will be produced within the Succeed project. This roadmap will serve to support the European Commission in preparing the 2014–2020 Work Programme for Research and Innovation.

Hildelies Balk in the National Library’s Reading Rooms

The Digitisation Days will be of interest to …?

‘Anyone who is working with digitised historical texts. These are often difficult to use because the software cannot decipher damaged originals or illegible characters. For example:

‘The software used to ‘read’ this (Dutch) text produces the following result:

VVt Venetien den 1.Junij, Anno 1618.
DJgn i f paffato te S’ aö’Jifeert mo?üen/bah
.)etgi’uotbciraetail)i.r/JtmelchontDecht
te / sbnbe bele btr felbrr geiufttceert baer bnber
eeniglje jprant o^fen/bie ftcb .met beSpaenfcbeu
enbeeemgljen bifet Cbeiiupcen berbonbru befe

‘The Dutch National Library and many other libraries are striving to make these types of historical text more usable to researchers by enhancing the quality of the OCR (optical character recognition). Since 2008, we have been involved in European projects set up to improve the usability of OCR’d texts – preferably automatically. The IMPACT Centre of Competence as well as the Digitisation Days are quite unique in that they bring together three interest groups:

• institutions with digitised collections (libraries, archives, museums)
• researchers working on means to improve access to digitised text (image recognition, pattern recognition, language technology)
• companies providing products and services in the field of digitisation and OCR.

‘Representatives of all of these groups will be taking part in the Digitisation Days and they offer participants a complete overview of the state of the art in document analysis, language technology and post-correction of OCR.’

What are the most important benefits from the Centre of Competence and the Digitisation Days, in your opinion?

‘The IMPACT Centre of Competence assists heritage institutions in taking important decisions. We evaluate available tools and report about them. Evaluation software of good quality is available as well. We also provide institutions with guidance and advice in digitisation issues by answering questions such as: what would be the best tools and methods for this particular institution? What quality can you expect from a solution? And what will it cost?’

‘The Digitisation Days offer a perfect opportunity for heritage institutions to get together and share experience and knowledge on issues such as: how to embed digitisation in your institution? How to deal with providers? Also: how do we start up new projects? Where do we find funding? On the second day, those who are interested are invited to join a workshop on the topic of the research agenda for digitisation. What should be the focus for the coming years? Should we focus on quantity or quality? How can we help shapeEuropean plans and budgets?’

Now that you mention Europe: IMPACT, IMPACT Centre of Competence, SUCCEED – the announcement of the Digitisation Days is packed with acronyms. Can you give us a bit of help here??

‘IMPACT was the first European research project aimed at improving access to historical texts. It started in 2008, at the initiative of, among others, the Dutch KB. When the project ended, a number of IMPACT partners set up the IMPACT Centre of Competence to ensure that the project results would be supported and developed. The Centre is not a project, but a standing organisation.’

‘Succeed is another European project, and, by definition, temporary. The objectives are in line with the IMPACT CoC, and the project involves some of the same partners. The aim is raise awareness about the results of European projects related to the digital library and to stimulate implementation. Before the CoC, it was not uncommon for prototypes to be left as they were after completion of a project. Thus the investments did not pay off.’

Will you really turn theory into practice?

‘Yes, most definitely! It is our prime focus for the conference. This is why we instituted the Succeed awards which will be handed out during the Digitisation Days; the Succeed awards recognise the best implementations of innovative technologies. The board has recently announced the winners.’

What do you personally look forward to most during the Digitisation Days?

‘To meeting everybody, to bringing together all these different parties. Colleagues from other institutions, researchers – this is exactly the right kind of meeting for generating exciting ideas and solutions.’

Hildelies Balk in de leeszalen van de KB

Voor wie zijn de Digitisation Days interessant?

‘Voor iedereen die te maken heeft met gedigitaliseerde, historische teksten. Die zijn vaak moeilijk bruikbaar omdat de leessoftware veel fouten maakt. Dat komt bij voorbeeld omdat het originele drukwerk zelf al slecht was, of omdat de drukletter slecht leesbaar is:

‘De software die de plaatjes moet omzetten in leesbare tekst maakt daarvan:

VVt Venetien den 1.Junij, Anno 1618.
DJgn i f paffato te S’ aö’Jifeert mo?üen/bah
.)etgi’uotbciraetail)i.r/JtmelchontDecht
te / sbnbe bele btr felbrr geiufttceert baer bnber
eeniglje jprant o^fen/bie ftcb .met beSpaenfcbeu
enbeeemgljen bifet Cbeiiupcen berbonbru befe

‘De KB en andere bibliotheken willen dit soort teksten in bruikbare vorm aanbieden aan wetenschappers. Dus zoeken we al sinds 2008 in Europees verband naar methoden om de teksten te verbeteren, liefst automatisch. Het unieke aan het IMPACT Centre of Competence én van de Digitisation Days is dat daar drie belangengroepen bij elkaar komen die elkaar versterken:

• instellingen met collecties die gedigitaliseerd zijn (bibliotheken, archieven, musea)
• onderzoekers die methoden ontwikkelen om gedigitaliseerde tekst te verbeteren (beeldherkenning en – verbetering, patroonherkenning, taaltechnologie)
• leveranciers van producten en diensten voor digitalisering en OCR (optical character recognition).

‘Door de aanwezigheid van al deze mensen krijgt de bezoeker in twee dagen tijd een compleet overzicht van wat er momenteel allemaal mogelijk is – op het gebied van documentanalyse, taaltechnologie en post-correctie van OCR.’

Wat zie jij als het grootste nut van het Centre of Competence en de Digitisation Days?

‘Het IMPACT Centre of Competence helpt erfgoedinstellingen belangrijke beslissingen te nemen. We evalueren bestaande tools en publiceren daarover. Er is zelfs heel goede evaluatiesoftware. En we leveren begeleiding; als een instelling wil gaan digitaliseren kunnen wij ze van advies dienen. Wat zijn de beste tools en methoden in hun specifieke geval? Wat voor kwaliteit mag je verwachten? Wat gaat het kosten?’

‘De Digitisation Days zijn een perfecte manier voor erfgoedinstellingen om elkaar te ontmoeten, uitgebreid ervaringen en kennis te delen. Bijvoorbeeld: Hoe ga je om met leveranciers? Hoe geef je digitalisering een plek in je organisatie? Maar ook: hoe zetten we nieuwe projecten op? Hoe vinden we geldstromen? Op de tweede dag is er een workshop waarin we met belangstellenden gaan praten over de onderzoeksagenda voor digitalisering. Waar moeten we de nadruk op leggen? Meer kwantiteit of meer kwaliteit? Hoe kunnen we de plannen en budgetten van Europa beïnvloeden?’

Nu je het over Europa hebt: IMPACT, IMPACT Centre of Competence, SUCCEED – de aankondiging van de Digitisation Days staat vol met afkortingen. Kun je een beetje orde scheppen in die chaos?

‘IMPACT was het eerste Europese onderzoeksproject voor verbetering van toegang tot historische teksten dat mede op initiatief van de KB in 2008 is gestart. Toen het project afgelopen was, hebben een aantal IMPACT-partners de handen ineengeslagen om ervoor te zorgen dat de resultaten van het project onderhouden en verder ontwikkeld zouden worden. Dat is het IMPACT Centre of Competence. Geen project, maar een staande organisatie.’

‘Succeed is weer een Europees project en dus tijdelijk. De doelstellingen liggen helemaal in lijn met het IMPACT CoC, en daarom zijn er deels dezelfde partners bij betrokken. Doel is om te zorgen dat eindresultaten van Europese projecten op het gebied van de digitale bibliotheek goed onder de aandacht worden gebracht zodat ze gebruikt gaan worden in de praktijk. In het verleden bleven prototypes nog wel eens op de plank liggen. Dat is zonde van de investering.’

Wordt de stap van theorie naar praktijk echt gezet?

‘Jazeker! Die willen we juist alle aandacht geven. Daarom reiken we tijdens de Digitisation Days de Succeed awards uit – prijzen voor de beste toepassingen van innovatieve oplossingen. De jury heeft onlangs de kandidaten en de winnaars bekend gemaakt.’

Waar verheug jijzelf je het meest op tijdens de Digitisation Days?

‘Op de ontmoeting, het bij elkaar brengen van al die belanghebbenden. Collega’s van andere instellingen, de onderzoekers – juist uit de ontmoeting komen vaak spannende ideeën en oplossingen voort.’

https://www.flickr.com/photos/116354723@N02/13757270124/

Is there any one still out there who thinks a hackathon is a malicious break-in? Far from it. It is the best way for developers and researchers to get together and work on new tools and innovations. The 2nd developers workshop / hackathon organised on 10-11 April by the Succeed Project was a case in point: bringing together people to work on new ideas and new inspiration for better OCR. The event was held in the “Claude Shannon” aula of the Department of Software and Computing Systems (DLSI) of the University of Alicante, Spain. Claude Shannon was a famous mathematician and engineer and is also known as the “father of information theory”. So it seems like a good place to have a hackathon!

Clemens explains what a hackathon is and what we hope to achieve with it for Succeed.

Same as last year, we again provided a wiki upfront with some information about possible topics to work on, as well as a number of tools and data that participants could experiment with before and during the event. Unfortunately there was an unexpectedly high number of no-shows this time – we try to keep these events free and open to everyone, but may have to think about charging at least a no-show fee in the future, as places are usually limited. Or did those hackers simply have to stay home to fix the heartbleed bug on their servers? We will probably never find out.

Collaboration, open source tools, open solutions

Nevertheless, there was a large enough group of programmers and researchers from Germany, Poland, the Netherlands and various parts of Spain eager to immerse themselves deeply into a diverse list of topics. Already in the introduction we agreed to work on open tools and solutions, and quickly identified some areas in which open source tool support for text digitisation is still lacking (see below). Actually, one of the first things we did was to set up a local git repository, and people were pushing code samples, prototypes and interesting projects to share with the group during both days.

https://www.flickr.com/photos/116354723@N02/13775777003/

What’s the status of open source OCR?

Accordingly, Jesús Dominguez Muriel from Digibís (the company that also made http://www.digibis.com/dpla-europeana/)  started an investigation into open source OCR tools and frameworks. He made a really detailed analysis of the status of open source OCR, which you can find here. Thanks a lot for that summary, Jesús! At the end of his presentation, Jesús also suggested an “algorithm wikipedia” – I guess something similar to RosettaCode but then specifically for OCR. This would indeed be very useful to share algorithms but also implementations and prevent reinventing (or reimplementing) the wheel. Something for our new OCRpedia, perhaps?

A method for assessing OCR quality based on ngrams

As turned out on the second day, a very promising idea seemed to be using ngrams for assessing the quality of an OCR’ed text, without the need for ground truth. Well, in fact you do still need some correct text to create the ngram model, but one can use texts from e.g. Project Gutenberg or aspell for that. Two groups started to work on this: while Willem Jan Faber from the KB experimented with a simple Python script for that purpose, the group of Rafael Carrasco, Sebastian Kirch and Tomasz Parkola decided to implement this as a new feature in the Java ocrevalUAtion tool (check the work-in-progress “wip” branch).

https://www.flickr.com/photos/116354723@N02/13775774723/

Jesús in the front, Rafael, Sebastian and Tomasz discussing ngrams in the back.

Aligning text and segmentation results

Another very promising development was started by Antonio Corbi from the University of Alicante. He worked on a software to align plain text and segmentation results. The idea is to first identify all the lines in a document, segment them into words and eventually individual charcaters, and then align the character outlines with the text in the ground truth. This would allow (among other things) creating a large corpus of training material for an OCR classifier based on the more than 50,000 images with ground truth produced in the IMPACT Project, for which correct text is available, but segmentation could only be done on the level of regions. Another great feature of Antonio’s tool is that while he uses D as a programming language, he also makes use of GTK, which has the nice effect that his tool does not only work on the desktop, but also as a web application in a browser.

OCR is complicated, but don’t worry – we’re on it!

Gustavo Candela works for the Biblioteca Virtual Miguel de Cervantes, the largest Digital Library in the Spanish speaking world. Usually he is busy with Linked Data and things like FRBR, so he was happy to expand his knowledge and learn about the various processes involved in OCR and what tools and standards are commonly used. His findings: there is a lot more complexity involved in OCR than appears at first sight. And again, for some problems it would be good to have more open source tool support.

In fact, at the same time as the hackathon, at the KB in The Hague, the ‘Mining Digital Repositories‘ conference was going on where the problem of bad OCR was discussed from a scholarly perspective. And also there, the need for more open technologies and methods was apparent:

[tweet 454528200572682241 hide_thread=’true’]

Open source border detection

One of the many technologies for text digitisation that are available in the IMPACT Centre of Competence for image pre-processing is Border Removal. This technique is typically applied to remove black borders in a digital image that have been captured while scanning a document. The borders don’t contain any information, yet they take up expensive storage space, so removing the borders without removing any other relevant information from a scanned document page is a desirable thing to do. However, there is no simple open source tool or implementation for doing that at the moment. So Daniel Torregrosa from the University of Alicante started to research the topic. After some quick experiments with tools like imagemagick and unpaper, he eventually decided to work on his own algorithm. You can find the source here. Besides, he probably earns the award for the best slide in a presentation…showing us two black pixels on a white background!

A great venue

All in all, I think we can really be quite happy with these results. And indeed the University of Alicante also did a great job hosting us – there was an excellent internet connection available via cable and wifi, plenty of space and tables to discuss in groups and we were distant enough from the classrooms not to be disturbed by the students or vice versa. Also at any time there was excellent and light Spanish food – Gazpacho, Couscous with vegetables, assorted Montaditos, fresh fruit…nowadays you won’t make hackers happy with just pizza anymore! Of course there were also ice-cooled drinks and hot coffee, and rumours spread that there were also some (alcohol-free?) beers in the cooler, but (un)fortunately there is no more documentary evidence of that…

To be continued!

If you want to try out any of the software yourself, just visit our github and have go! Make sure to also take a look at the videos that were made with participants Jesús, Sebastian and Tomasz, explaining their intentions and expectations for the hackathon. And at the next hackathon, maybe we can welcome you too amongst the participants?

The KB National Library of the Netherlands has been investigating named entity recognition (NER) and linked data technologies for a while now in projects such as IMPACT and STITCH+, and we felt it was about time to approach this on a production scale. So we decided to produce (open source) software, trained models as well as raw training data for NER software applications specifically for digitised historical newspapers as part of the project.

What is named entity recognition (NER)?

Named entity recognition is the process of identifying and classifying entities such as persons, locations and organisations in the full-text in order to enhance searchability. There are basically two types of approaches, a statistical and a rule based one. Rule based systems rely mostly on grammar rules defined by linguists, while statistical systems require large amounts of manually produced training data that they can learn from. While both approaches have their benefits and drawbacks, we decided to go for a statistical tool, the CRF–NER system from Stanford University. In comparison, this software proved to be the most reliable, and it is supported by an active user community. Stanford University has an online demo where you can try it out: http://nlp.stanford.edu:8080/ner/.

Example of Wikipedia article for Albert Einstein, tagged with the Stanford NER tool

Requirements & challenges

There are some particular requirements and challenges when applying these techniques to digital historical newspapers. Since full-text for more than 10 million pages will be produced in the project, one requirement for our NER tool was that it should be able to process large amounts of texts in a rather short time. This is possible with the Stanford tool,  which as of version 1.2.8 is “thread-safe”, i.e. it can run in parallel on a multi-core machine. Another requirement was to preserve the information about where on a page a named entity has been detected – based on coordinates. This is particularly important for newspapers: instead of having to go through all the articles on a newspaper page to find the named entity, it can be highlighted so that one can easily spot it even on very dense pages.

Then there are also challenges of course – mainly due to the quality of the OCR and the historical spelling that is found in many of these old newspapers. In the course of 2014 we will thus collaborate with the Dutch Institute for Lexicology (INL), who have produced modules which can be used in a pre-processing step before the Stanford system and that can to some extent mitigate problems caused by low quality of the full-text or the appearance of historical spelling variants.

The Europeana Newspapers NER workflow

For Europeana Newspapers, we decided to focus on three languages: Dutch, French and German. The content in these three languages makes up for about half of the newspaper pages that will become available through Europeana Newspapers. For the French materials, we cooperate with LIP6-ACASA, for Dutch again with INL. The workflow goes like this:

1. We receive OCR results in ALTO format (or METS/MPEG21-DIDL containers)
2. We process the OCR with our NER software to derive a pre-tagged corpus
3. We upload the pre-tagged corpus into an online Attestation Tool (provided by INL)
4. Within the Attestation Tool, the libraries make corrections and add tags until we arrive at a “gold corpus”, i.e. all named entities on the pages have been manually marked
5. We train our NER software based on the gold corpus derived in step (4)
6. We process the OCR again with our NER software trained on the gold corpus
7. We repeat steps (2) – (6) until the results of the tagging won’t improve any further
   

   Screenshot of the NER Attestation Tool

Preliminary results

Named entity recognition is typically evaluated by means of Precision/Recall and F-measure. Precision gives an account of how many of the named entities that the software found are in fact named entities of the correct type, while Recall states how many of the total amount of named entities present have been detected by the software. The F-measure then combines both scores into a weighted average between 0 – 1. Here are our (preliminary) results for Dutch so far:

These figures have been derived from a k-fold cross-evaluation of 25 out of 100 manually tagged pages of Dutch newspapers from the KB. The results confirm the fact that the Stanford system tends to be a bit “conservative”, i.e. it has a somewhat lower recall for the benefit of higher precision, which is also what we wanted.

Conclusion and outlook

Within this final year of the project we are looking forward to see in how far we can still boost these figures by adopting the extra modules from INL, and what results we can achieve on the French and German newspapers. We will also investigate software for linking the named entities to additional online resource descriptions and authority files such as DBPedia or VIAF to create Linked Data. The crucial question will be how well we can disambiguate the named entities and find a correct match in these resources. Besides, if there is time, we would also want to experiment with NER in other languages, such as Serbian or Latvian. And, if all goes well, you might already hear more about this at the upcoming IFLA newspapers conference “Digital transformation and the changing role of news media in the 21st Century“.

References

• Get the source code of the NER tool for Europeana Newspapers: https://github.com/KBNLresearch/europeananp-ner/
• Get models and training data for the NER tool for Europeana Newspapers:
  http://lab.kbresearch.nl/static/html/eunews.html
• The Stanford University NER tool:
  http://www-nlp.stanford.edu/software/CRF-NER.shtml
• The INL NER tool:
  http://www.digitisation.eu/tools/browse/toolbox-for-lexicon-building/named-entities-recognition-tool-nert/