Palmirani, Paschke, et al.: Slides of LegalRuleML Tutorial at Jurix 2012

Professor Dr. Monica Palmirani of the University of Bologna has posted slides of the LegalRuleML Tutorial given at Jurix 2012 on 17 December 2012, in Amsterdam.

The slides include a general tutorial by Prof. Palmirani and colleagues, and a use case by Professor Dr. Adrian Paschke of Freie Universität Berlin entitled LegalRuleML for Legal Reasoning in Patent Law.

Click here for the program of the tutorial.

LegalRuleML is a markup language, based on RuleML, for modeling legal rules.

LegalRuleML is currently being developed by the OASIS LegalRuleML Technical Committee, which is co-chaired by Professor Palmirani and Dr. Guido Governatori of NICTA.

Legal Informatics Papers/Posters at ICEGOV 2012

Here are the legal informatics papers and posters (that I’ve been able to identify) to be presented at ICEGOV 2012: International Conference on Theory and Practice of Electronic Governance, being held 22-25 October 2012 at the University at Albany Center for Technology in Government, in Albany, New York, USA.

Click here for the conference program.

The Twitter hashtag for the conference is #icegov

[If you know of other legal informatics papers being given at the conference, please let us know about them in the comments to this post. For abstracts and full text, please contact the authors]:

• Vasiliy Burov, Evgeny Patarakin, Boris Yarmakhov: A Crowdsourcing Model for Public Consultations on Draft Laws
• Adriana Simeao Ferreira, Daniel Goncalves de Melo, Leondeniz Freitas: The Importance of Electronic Accessibility in Brazilian Juridical Electronic Process
• Josiah Heidt, Jackeline Solivan: Regulation Room: Moving Towards Civic Participation 2.0
• Kincho Law, Gloria Lau: REGNET: Regulatory Information Management, Compliance and Analysis
• Fabro Steibel: Designing Online Deliberation Using Web 2.0 Technologies: Drafting a Bill of Law on Internet Regulation in Brazil
• Siddharth Taduri, Gloria Lau, Kincho Law, Jay Kesan: A Patent System Ontology for Facilitating Retrieval of Patent Related Information

Kacsuk on The Mathematics of Patent Claim Analysis

Zsófia Kacsuk, MSc., of KacsukPatent, has published The Mathematics of Patent Claim Analysis, forthcoming in Artificial Intelligence and Law. Here is the abstract:

In patent law most of the crucial legal questions such as patentability and infringement are linked to the patent claims. The European Patent Office regards patent claims as a set of independent features which are examined separately in a more or less formal way. The author has found that this approach allows for developing a simple mathematical model which treats patent claim features as logical statements and patent claims as compound statements wherein the individual statements are connected by logical connectives. The proposed mathematical model provides a uniform system for examining various legal questions that are dealt with separately under current case law, moreover, it allows for developing an expert system for resolving complex legal situations and for automating the evaluation of a large number of patent claim variants that is currently not possible.

Liu & Shih on Hybrid-Patent Classification Based on Patent-Network Analysis

Professor Dr. Duen-Ren Liu and Meng-Jung Shih, both of National Chiao Tung University Institute of Information Management, have published Hybrid-patent classification based on patent-network analysis, forthcoming in Journal of the American Society for Information Science and Technology (JASIST). Here is the abstract:

Effective patent management is essential for organizations to maintain their competitive advantage. The classification of patents is a critical part of patent management and industrial analysis. This study proposes a hybrid-patent-classification approach that combines a novel patent-network-based classification method with three conventional classification methods to analyze query patents and predict their classes. The novel patent network contains various types of nodes that represent different features extracted from patent documents. The nodes are connected based on the relationship metrics derived from the patent metadata. The proposed classification method predicts a query patent’s class by analyzing all reachable nodes in the patent network and calculating their relevance to the query patent. It then classifies the query patent with a modified k-nearest neighbor classifier. To further improve the approach, we combine it with content-based, citation-based, and metadata-based classification methods to develop a hybrid-classification approach. We evaluate the performance of the hybrid approach on a test dataset of patent documents obtained from the U.S. Patent and Trademark Office, and compare its performance with that of the three conventional methods. The results demonstrate that the proposed patent-network-based approach yields more accurate class predictions than the patent network-based approach.

Magdy & Jones on Examining the Robustness of Evaluation Metrics for Patent Retrieval with Incomplete Relevance Judgements

Walid Magdy and Dr. Gareth J. F. Jones, both of the Dublin City University School of Computing, will present a paper entitled Examining the Robustness of Evaluation Metrics for Patent Retrieval with Incomplete Relevance Judgements, at CLEF 2010: The Conference on Multilingual and Multimodal Information Access Evaluation, to be held 20-23 September 2010 in Padua, Italy. Here is the abstract:

Recent years have seen a growing interest in research into patent retrieval. One of the key issues in conducting information retrieval (IR) research is meaningful evaluation of the effectiveness of the retrieval techniques applied to task under investigation. Unlike many existing well explored IR tasks where the focus is on achieving high retrieval precision, patent retrieval is to a significant degree a recall focused task. The standard evaluation metric used for patent retrieval evaluation tasks is currently mean average precision (MAP). However this does not reflect system recall well. Meanwhile, the alternative of using the standard recall measure does not reflect user search effort, which is a significant factor in practical patent search environments. In recent work we introduce a novel evaluation metric for patent retrieval evaluation (PRES) (Magdy and Jones, SIGIR 2010). This is designed to reflect both system recall and user effort. Analysis of PRES demonstrated its greater effectiveness in evaluating recall-oriented applications than standard MAP and Recall. One dimension of the evaluation of patent retrieval which has not previously been studied is the effect on reliability of the evaluation metrics when relevance judgements are incomplete. We provide a study comparing the behaviour of PRES against the standard MAP and Recall metrics for varying incomplete judgements in patent retrieval. Experiments carried out using runs from the CLEF-IP 2009 datasets show that PRES and Recall are more robust than MAP for incomplete relevance sets for this task with a small preference to PRES as the most robust evaluation metric for patent retrieval with respect to the completeness of the relevance set.

For the full text of the paper, please contact the authors.

Thanks to the authors for providing the abstract.

Wechsler on Japanese, Chinese, Korean, and Indian Patent Information: Asia’s Rising Role in Technology Disclosure through the Patent System

Andrea Wechsler, LL.M., of Max-Planck-Institut für Geistiges Eigentum, Wettbewerbs- und Steuerrecht has published Japanese, Chinese, Korean, and Indian Patent Information: Asia’s Rising Role in Technology Disclosure through the Patent System, 2 Tsinghua China Law Review, Issue No. 1, Fall 2009, pages 101-158.

Here is the abstract:

Patent information – as a form of technology disclosure – serves an important function in business strategy as well as in industrial policy making. This study first discusses the role of patent information for technology disclosure before showing the rising importance of patents in Asia (Japan, Korea, China, India) as source of technological information. It demonstrates both the substantial increase of Asian patents in force from the 1980s to 2006 and the increase of Asian patent grants from the 1990s to 2006. Furthermore, Asian patent grants for every billion U.S. Dollar of the gross domestic product (in current prices of the period measured) are analyzed as is the ratio of patent grants to patent applications in Japan, Korea, China, and India. Analyses of the availability of and access to patent information in Asia demonstrate that patent information is easily accessible, while its relevance is hard to detect. In consequence, this paper argues that the increasing relevance of Asian patent information needs to be complemented with the provision of competitive databases that contain value-added patent information allowing for high quality search results.

June 30 Webcast: e-Justice Track of SEPG Europe 2010

A free Webcast of the e-Justice Track of the SEPG Europe 2010 Conference, will be held 30 June 2010. The event will be Webcast from the University of Porto Faculty of Engineering in Porto, Portugal.

Here are the major presentations to be given during the event:

• Mr José Magalhães, Secretary of State of Justice and the Judiciary Modernization, The quality of software as a sustainability factor for the use of the information technologies within the justice system;
• The quality of software as a sustainability factor for the use of the information technologies within the justice system – the Portuguese experience;
• Mr Bruno Sá, Chairman of the Information Technologies Institute of the Ministry of Justice, The dematerialization of processes in the courts;
• Mr António Figueiredo, Chairman of the Registers and Notaries Institute, The interoperability and the innovating registers services;
• Mr. Pedro Santos, Management Director of Industrial Property National Institute, On-Line Trade Marks and Patents;
• Mr Domingos Farinho, Director of the Alternative Dispute Resolution Means Cabinet, On-Line Alternative Dispute Resolution Means;
• Mrs Zaida Chora, Deputy Chairman of the Information Technologies Institute of the Ministry of Justice, The Development of Information Systems within the Public Administration;
• Mr Ponciano Oliveira, Deputy Chairman of the Information Technologies Institute of the Ministry of Justice, The use of information technologies within the justice systems on the international context.

Thanks to Stéphane Cottin for this information.

Call for Papers: PaIR 2010: Workshop on Patent Information Retrieval

A call for papers — with submission deadline of 30 June 2010 — has been issued for PaIR 2010: The 3rd International Workshop on Patent Information Retrieval, to be held 26 October 2010, in Toronto, Ontario, Canada.

The workshop is collocated with CIKM 2010: The 19th ACM International Conference on Information and Knowledge Management.

According to the call, PaIR 2010 “solicits two types of papers: ‘research/solutions’ and ‘IP/needs’ papers.”

“Research/solutions” papers are invited on the following topics:

• “Cross-lingual information retrieval
• Patent classification
• Ontology-based retrieval
• Latent Semantic Analysis
• Information retrieval evaluation
• Evaluation frameworks
• Test collections
• Large-scale information retrieval experiments
• Parallel and distributed information retrieval
• Ranking strategies
• Query validation and query quality analysis
• Query expansion
• Interactive retrieval
• Session-based information retrieval
• User modeling
• Handling of noisy data (OCR/spelling/typing errors)
• XML retrieval
• NLP / Natural Language Processing”

“IP/needs” papers, which “shall present research challenges,” are invited on the following topics:

• “Patent search workflow
• Patent search strategies
• Information need of the patent researcher
• Shortcomings of current patent search tools
• Case studies
• Challenges in patent search
• Patent life cycle
• Quality of patent data”

For more information, please see the call for papers.

Report on AsPIRe’10: The 1st International Workshop on Advances in Patent Information Retrieval

Dr. Allan Hanbury of the Information Retrieval Facility, and Veronika Zenz and Helmut Berger, both of Matrixware Information Services, have posted Workshop Report: 1st International Workshop on Advances in Patent Information Retrieval (AsPIRe’10), for the workshop held 28 March 2010 in Milton Keynes, England, UK, in conjunction with ECIR 2010: The 32nd European Conference on Information Retrieval.

The report summarizes the papers delivered at the workshop. Three of those papers reported research on the AsPIRe’10 dataset, “a collection of 400,000 patent documents in XML format.”

Here are the authors and titles of the papers presented at AsPIRe’10, with links to full text where available:

• Tao Jiang, Benjamin K. Tsou and Bin Lu, Part-of-speech Language Model for N-Best List Re-ranking in Experimental Chinese-English SMT;
• Richard Bache and Leif Azzopardi, Identifying Retrievability-Improving Model Features to Enhance Boolean Search for Patent Retrieval;
• Suzane Verberne, Eva D’hondt, Nelleke Oostdijk, and Cornelis H.A. Koster, Quantifying the Challenges in Parsing Patent Claims;
• Walid Magdy and Gareth J.F. Jones, A New Metric for Patent Retrieval Evaluation;
• Veronika Zenz, Sebastian Wurzer, Michael Dittenbach, and Edgardo Ambrosi, On the Effects of Indexing and Retrieval Models in Patent Search and the Potential of Result Set Merging.

Bashir & Rauber on Improving Retrievability of Patents in Prior-Art Search

Shariq Bashir and Professor Dr. Andreas Rauber, both of the Vienna University of Technology Information Software & Engineering Group, will present a paper entitled Improving Retrievability of Patents in Prior-Art Search, at ECIR 2010: The 32nd European Conference on Information Retrieval, to be held 28-31 March 2010 at Open University, in Milton Keynes, England, United Kingdom. Here is the abstract:

Prior-art search is an important task in patent retrieval. The success of this task relies upon the selection of relevant search queries. Typically terms for prior-art queries are extracted from the claim fields of query patents. However, due to the complex technical structure of patents, and presence of terms mismatch and vague terms, selecting relevant terms for queries is a difficult task. During evaluating the patents retrievability coverage of prior-art queries generated from query patents, a large bias toward a subset of the collection is experienced. A large number of patents either have a very low retrievability score or can not be discovered via any query. To increase the retrievability of patents, in this paper we expand prior-art queries generated from query patents using query expansion with pseudo relevance feedback. Missing terms from query patents are discovered from feedback patents, and better patents for relevance feedback are identified using a novel approach for checking their similarity with query patents. We specifically focus on how to automatically select better terms from query patents based on their proximity distribution with prior-art queries that are used as features for computing similarity. Our results show, that the coverage of prior-art queries can be increased significantly by incorporating relevant queries terms using query expansion.

Thanks to the authors for sending the abstract.