Workshop Schedule

Contact the workshop organizers for immediate assistance in case you didn't receive an e-mail from Underline.

Time CET Time EDT Event
15:00 - 15:05 09:00 - 09:05 Opening
15:05 - 16:05 09:05 - 10:05 Keynote: Noriko Kando
16:05 - 16:10 10:05 - 10:10 Break
16:10 - 17:30 10:10 - 11:30

Chemical Reaction Reference Resolution in Patents
Hiyori Yoshikawa, Saber A. Akhondi, Camilo Thorne, Christian Druckenbrodt, Ralph Hoessel, Zenan Zhai, Jiayuan He, Timothy Baldwin and Karin Verspoor

Prior Art Search and Reranking for Generated Patent Text
Jieh-Sheng Lee and Jieh Hsiang

Modular Development in Patent AI Space: A Case Study
Mahesh Maan, Sam Zellner and Anirudh Sanutra

17:30 - 17:40 11:30 - 11:40 Break
17:40 - 18:25 11:40 - 12:25

PatentExplorer: Refining Patent Search with Domain-specific Topic Models
Mark Buckley, Sophia Althammer and Arber Qoku

WIPO Pearl – Insights into the Concept Map Search and Linguistic Search
Geoffrey Westgate, Cristina Valentini (WIPO: World Intellectual Property Organization)

The next generation AI-based Prior Art Search tools can be sustainable and transparent.
Linda Andersson, Peter Pollak, Tobias Fink, Florina Piroi

18:25 - 19:10 12:25 - 13:10 Break
19:10 - 20:10 13:10 - 14:10 Keynote: Osmat Jefferson
20:10 - 20:15 14:10 - 14:15 Break
20:15 - 21:25 14:15 - 15:25

Linguistically Informed Masking for Representation Learning in the Patent Domain
Sophia Althammer, Mark Buckley, Sebastian Hofstätter and Allan Hanbury

PatentMatch: A Dataset for Matching Patent Claims & Prior Art
Julian Risch, Nicolas Alder, Christoph Hewel and Ralf Krestel

A Multimodal Approach for Semantic Patent Image Retrieval
Kader Pustu-Iren, Gerrit Bruns and Ralph Ewerth

21:25 - 21:35 15:25 - 15:35 Break
21:35 - 22:35 15:35 - 16:35 Panel Presentations
21:35 - 22:35 15:35 - 16:35

AI in and for Patent Analytics: A hype or an efficient support tool for patent analysts?
Irene Kitsara (World Intellectual Property Organization)

IPLodB: Using linked open data in the innovation field - opportunities unveiled and problems encountered
Dolores Modic (IPLodB project, Nord University)

Challenges for patent practitioners to apply AI in their workflows
Christoph Hewel (Patent Lawyer at BETTEN & RESCH)

Artificial Intelligence Opportunities in the Patent Grant Process: An IP office perspective
Alexander Klenner-Bajaja (Head of Data Science, European Patent Office)

PATENTABILITY SEARCH: University's Perspective
Tanja Sovic (Head of Patent & Licence Management, Technische Universität Wien)

22:35 - 23:20 16:35 - 17:20 Panel Discussions
23:20 - 23:25 17:20 - 17:25 Closing

Workshop Registration

Registration to this workshop is done via the SIGIR registration page.
Note that when you register to workshops or tutorials only, there is a Workshop entry fee, to which $USD 10 are charged per each workshop registration

Keynote Speakers

We are honoured to have Prof. Noriko Kando and Prof. Osmat Jefferson as keynote speakers.

Creating Future Values in Information Access Research through NTCIR: Reflection of the 20-Year History of Patent-Related Shared Tasks and the Way Ahead.

Noriko Kando

Speaker: Noriko Kando Ph.D (Library and Information Science)
Information and Society Research Division,
National Institute of Informatics (NII)

Abstract: NTCIR (NII Testbeds and Community for Information access Research) is a series of evaluation workshops designed to enhance the research in information access technologies, such as information retrieval, question answering, and summarization using East-Asian languages, by providing infrastructures for research and evaluation. The project started late 1997 and has the workshop in 18-month cycle. It is a community-led activity and each round of NTCIR hosts several research tracks called "tasks", which are planned and organized by groups of international researchers. This talk focuses on Patent-related tasks and reviews how each of them has evolved and impacts to the research community and the society. Finally some thoughts on the future direction will be presented.

Short Bio: Noriko Kando is a professor in the Information-society Research Division of the National Institute of Informatics (NII), Tokyo, Japan, and has been co-appointed as a professor in the Department of Informatics at the Graduate University of Advanced Studies, Japan. She is one of the NTCIR initiators (, an evaluation of information-access technologies, such as information retrieval, summarization, question answering, and text mining, using East Asian languages and English documents. She has been the main designer of many and various retrieval tasks: patent retrieval, cross-lingual IR, opinion analysis, complex question answering, community Q&A, geo-time search.

(full profile:

Open toolkits for problem solvers in the science & technology-based innovation ecosystem.

Osmat Jefferson

Speaker: Osmat Jefferson PhD MInt Law
Faculty of Science, School of Information Systems,
Queensland University of Technology (QUT);
Director of Product Development, Cambia

Abstract: The Lens sources, merges, and links diverse open scholarly works and patents to inform discovery, analysis, decision-making, and partnering options on platform. The created and shared applications and toolkits are designed to optimize individual and institutional effectiveness in problem solving. In this presentation, I’ll introduce the role of the Lens in the dynamic and evolving innovation system, describe its architecture, built upon a metaRecord concept, and share its new experiment of using open toolkits to amplify a collective action solution to the problem of problem solving.

Short Bio: Osmat Jefferson's interests include science-enabled tools to solve societal problems. In the past thirty or so years of her professional life, Osmat was a school teacher, a desk librarian, a first aid volunteer in war zone, a research and lab leader, a business owner, and a research professor. She researched applied agricultural problems in the field and in the labs of various countries around the globe, built, and co-developed capabilities for local scientists. Intrigued by the dynamic and changing nature of innovation systems, she investigates linkages between various knowledge silos within these systems, including scientific and technological information and intellectual property and their influence on economy and society. She and the Lens team build new open toolkits for problems solvers. Osmat now leads the development of products at, an open and global platform designed by to render science-and technology-enabled problem solving more effective, efficient and inclusive.

(full profile: and

Panel discussion: "Artificial Intelligence and Patent Analysis: Friends or Foes?"

We are happy to have experts from both academia and IP industry:

IPLodB: Using linked open data in the innovation field - opportunities unveiled and problems encountered

Abstract: The short talk addresses the linked open data (LOD) approach for enabling access to (linked) patent information. We also touch upon the IPLodB project, which takes advantage of two datasets that follow the LOD principles and are published by two reputable organizations, the European Patent Office and the Springer Nature. These two datasets represent the core on which we started building a new patent-centric LOD sub-cloud. Hence, we will look at AI and patent analysis from a linked open data perspective and try to discuss its technological impact for future developments.

Challenges for patent practitioners to apply AI in their workflows

Abstract: Patent practice has a long history. As a consequence, the internal structure of patent law firms and their external interaction with clients, patent offices and courts is well established. Furthermore, also the workflows in patent prosecution are precisely defined. Such workflows in particular concern drafting and filing a patent application, prosecuting the application in the examination proceedings at a patent office until patent grant, and sometimes post grant proceedings (like revocation and litigation).
It comes thus with no surprise that applying disruptive technologies like AI implies a huge hurdle for the patent industry. In the panel discussion I will present my view as a patent attorney of the concrete obstacles and some ideas of how they might be overcome. Such obstacles can especially be found in the internal structure of law firms and their business model. In particular, due to a time-based revenue model and the rather conservative nature of patent practitioners, there is high reluctance to invest (and at least in short-term loose) time trying new and potentially poorly conceived technologies.
It therefore appears advisable to attempt adapting AI-based software solutions to the patent practitioner's needs and nature, in order to increase the level of confidence: Solutions which are custom-tailored to the patent-prosecution workflows and which imply a proven effect of gaining time for the patent practitioner. This does not only require advances in AI technology but also a profound understanding of the patent-prosecution workflows.

Artificial Intelligence Opportunities in the Patent Grant Process: An IP office perspective

Alexander Klenner

Panellist: Alexander Klenner-Bajaja
Head of Data Science
European Patent Office

Abstract: Patents have much to offer in terms of artificial intelligence challenges. The filing of a patent application sounds like a enumeration of machine learning tasks: An application needs to be routed to the correct team (classification), it needs to be translated (neural machine translation) and last but not least it needs to be precisely classified within the CPC (Classification again). What happens next is a search for prior art: An information retrieval task that also benefits already today from machine learning. The information in patents is stored in figures (computer vision) and unstructured text (natural language processing), which makes it even more interesting to apply latest deep learning breakthroughs to solve challenges around patents. The citation graph of all prior art is waiting to be explored by graph neural networks. However patents are also different: they are written in a legal and technical language that uses different syntax and different terminology compared to the internet in general (i.e. usual off the shelf trained models). The drawings are not those of cats and dogs, but of technical nature, in black and white. In this talk some of the challenges will be highlighted and we show how they are approached and solved at the European Patent Office.

AI in and for Patent Analytics: A hype or an efficient support tool for patent analysts?

Irene Kitsara

Panellist: Irene Kitsara
World Intellectual Property Organization

Abstract: Over the years, different automation tools for patent analytics tasks were proposed to management and patent information professionals, promising efficiency, reduction of time and necessary human resources. Patent information professionals have often been skeptical, raising concerns about quality, precision, transparency and control of the process and the outcome. With the AI advancements and related trend, governments, businesses, and individuals are eager to leverage the potential of AI and deploy them in their workflow. While AI or “AI-powered” tools start appearing, and AI is explored by IP offices and academia, two questions arise: is it working and is it worth it?
The future of patent analytics is expected to include AI, even if the exact form and extent are not yet clear. In this talk we will share some thoughts and observations about the status of AI tools for patent analytics, related benefits and challenges. We will use as basis for these thoughts a. WIPO`s exploratory work (2016 and ongoing work) on the use of open source tools and machine learning for patent analytics tasks in the framework of preparation of related methodological resources; and b. USPTO`s report (2020) comparing the performance of a patent professional team using traditional search and analysis approaches for the WIPO Technology Trends report on AI (2019) with the results of an AI model to retrieve and group AI-related patent documents, using WIPO`s patent dataset as benchmark.

PATENTABILITY SEARCH: University's Perspective

Tanja Sovic

Panellist: Tanja Sovic
Head of Patent & Licence Management
Technische Universität Wien

Abstract: Prior art search is crucial for the university's research. Being aware of relevant literature and patents related to the research topics can proof that our work is unique. Accelerated technological development and increasing number of interdisciplinary collaborations between different scientific areas lead to the expanding complexity in the prior art search. How can AI support these trends?