Blog

Machine Learning

Accepted Workshop @ECIR2019: The 1st Interdisciplinary Workshop on Algorithm Selection and Meta-Learning in Information Retrieval (AMIR)

Our proposal for the “1st Interdisciplinary Workshop on Algorithm Selection and Meta-Learning in Information Retrieval (AMIR)“, to be held at the  41st European Conference on Information Retrieval (ECIR), was accepted. AMIR will take place on the 14th of April 2019 in Cologne, Germany. The algorithm selection problem describes the challenge of identifying the best algorithm for a given problem space. In many domains, particularly artificial intelligence, the algorithm selection problem is well studied, and various approaches and tools exist to tackle it in practice. Especially through meta-learning impressive performance improvements have been achieved. The information retrieval (IR) community, however, has paid little attention to the algorithm selection problem, although the problem is highly relevant in information retrieval. AMIR will bring Read more…

Machine Learning

ParsRec: A Novel Meta-Learning Approach to Recommending Bibliographic Reference Parsers

Our manuscript “ParsRec: A Novel Meta-Learning Approach to Recommending Bibliographic Reference Parsers” was accepted for publication at the 26th Irish Conference on Artificial Intelligence and Cognitive Science (AICS). It is an extended version of our recently presented poster “ParsRec: Meta-Learning Recommendations for Bibliographic Reference Parsing” at the ACM RecSys conference. The bibliographic BibTeX data is as follows. @InProceedings{TkaczykBeel2018, author = {Tkaczyk, Dominika and Gupta, Rohit and Cinti, Riccardo and Beel, Joeran}, title = {ParsRec: A Novel Meta-Learning Approach to Recommending Bibliographic Reference Parsers}, booktitle = {26th Irish Conference on Artificial Intelligence and Cognitive Science (AICS)}, year = {2018}, volume = {5}, number = {1}, pages = {31–42}, } 1. Introduction Bibliographic reference parsing is a well-known task in scientific information extraction Read more…

Research

Participate in the “Track Your Daily Routine” Research Study About Your Smartphone Usage and Your Personality

A colleague of mine has initiated a new research project to analyse smartphone users’ usage behaviour and personality. He and his team have released an Android app named TYDR: Track Your Daily Routine. With the data from TYDR, they want to research if they can estimate the personality of a smartphone user by the data that can be collected automatically. This could eventually lead to not needing to fill out questionnaires anymore. There are potential benefits for mobile health apps and recommender systems – apps could know what type of person the user is and adapt to his/her needs. The main features include: Personality evaluation Visualization of your visited locations Photo statistics Music statistics Calls statistics Steps taken statistics App usage statistics Read more…

Recommendations as-a-Service (RaaS)

The Architecture of Mr. DLib’s Scientific Recommender-System API

Our manuscript “The Architecture of Mr. DLib’s Scientific Recommender-System API” got accepted at the “26th Irish Conference on Artificial Intelligence and Cognitive Science” (AICS), and here is the pre-print version. The bibliographic BibTeX data is: @InProceedings{Beel2018MDLArch, author = {Beel, Joeran and Collins, Andrew and Aizawa, Akiko}, title = {The Architecture of Mr. DLib’s Scientific Recommender-System API}, booktitle = {Proceedings of the 26th Irish Conference on Artificial Intelligence and Cognitive Science}, year = {2018}, volume = {26}, volumes = {1}, number = {26}, pages = {1–12}, abstract = {Recommender systems in academia are not widely available. This may be in part due to the difficulty and cost of developing and maintaining recommender systems. Many operators of academic products such as digital Read more…

Machine Learning

Best-Paper Award for our Publication “Implementing Neural Turing Machines” at the 27th International Conference on Artificial Neural Networks

We received the best-paper award at the 27th International Conference on Artificial Neural Networks (ICANN 2018) for our paper Implementing Neural Turing Machines. Our student, and co-author of the paper, Mark Collier was at ICANN to present our work about implementing a Neural Turing Machine. Neural Turing Machines (NTMs) are an instance of Memory Augmented Neural Networks, a new class of recurrent neural networks which decouple computation from memory by introducing an external memory unit. Neural Turing Machines have demonstrated superior performance over Long Short-Term Memory Cells in several sequence learning tasks. A number of open source implementations of Neural Turing Machines exist but are unstable during training and/or fail to replicate the reported performance of NTMs. This paper presents the details Read more…

Recommender Systems

Report/Photos from the 12th ACM Conference on Recommender Systems in Vancouver

Today, the 12th ACM Conference on Recommender Systems began in Vancouver, Canada. We attend and will present our work on meta-learning reference parsing tools in which we treat reference extraction from scientific articles as a recommendation problem. If you also attend the conference, visit us during the poster session on Thursday. So far, it has been a great conference with many exciting talks. A few of the many great presentations are the following Why I like it: Multi-task Learning for Recommendation and Explanation We describe a novel, multi-task recommendation model, which jointly learns to perform rating prediction and recommendation explanation by combining matrix factorization, for rating prediction, and adversarial sequence to sequence learning for explanation generation. The result is evaluated using real-world Read more…

Machine Learning

An Empirical Comparison of Syllabuses for Curriculum Learning (Pre-Print)

Update 12/11/2018: Our paper has been accepted at AICS 2018 and will be presented at the conference in December. We have published a pre-print (now available on Arxiv) which outlines our work comparing different syllabuses for curriculum learning. Neural networks are typically trained by repeatedly randomly selecting examples from a dataset and taking steps of stochastic gradient descent. Curriculum learning is an alternative approach to training neural networks, inspired by human learning in which training examples are presented according to a syllabus typically of increasing “difficulty”. Curriculum learning has shown some impressive empirical results, but little is known about the relative merits of different syllabuses. In this work, we provide an empirical comparison of a number of syllabuses found in Read more…

Machine Learning

Proposal for the 1st Interdisciplinary Workshop on Algorithm Selection and Meta-Learning in Information Retrieval (AMIR)

Lars Kotthoff and I have applied to organize the 1st Interdisciplinary Workshop on Algorithm Selection and Meta-Learning in Information Retrieval (AMIR) at the 41st European Conference on Information Retrieval (ECIR). Let’s cross fingers and hope it will get accepted. In the following, you find the proposal (also available on ResearchGate as PDF). @InProceedings{BeelKotthoff2018, author = {Beel, Joeran and Kotthoff, Lars}, title = {Proposal for the 1st Interdisciplinary Workshop on Algorithm Selection and Meta-Learning in Information Retrieval (AMIR)}, booktitle = {ResearchGate Repository}, year = {2018}, pages = {1–6}, doi = {10.13140/RG.2.2.14548.65922}, url = {https://www.researchgate.net/publication/328965675_Proposal_for_the_1st_Interdisciplinary_Workshop_on_Algorithm_Selection_and_Meta-Learning_in_Information_Retrieval_AMIR}, abstract = {The algorithm selection problem describes the challenge of identifying the best algorithm for a given problem space. In many domains, particularly artificial intelligence, the algorithm selection problem Read more…

Jobs & Internships

Open Call for “Government of Ireland Postgraduate Scholarship Programme 2019”

The Irish Research Council (IRC) has published a new call for its “Government of Ireland Postgraduate Scholarship” programme. We are eligible to supervise applicants during their application process and act as PhD supervisor for the 4-year period of the scholarship. Hence, if you are interested in doing a PhD at Trinity College Dublin in the field of machine learning or recommender systems, or any other of our research fields, please contact us. From their website The Government of Ireland Postgraduate Scholarship Programme is an established national initiative, funded by the Department of Education and Skills and managed by the Council. In 2017, we invested in a total of 1,179 postgraduate scholars, with over 5,000 individual scholarships for excellent research awarded Read more…

Machine Learning

3rd Call for EU Marie Curie EDGE Fellowships (e.g. in Machine-Learning or Recommender-Systems Research)

The 3rd call for EU Marie Curie EDGE fellowships has been published. We successfully supported the application of one EDGE fellow a year ago, and we would be happy to support talented candidates this year, too. So, if you are interested in an EDGE fellowship in the field of machine learning, recommender systems or another of our research areas, please contact us. Let us know some details about your yourself and your project idea. EDGE is Marie Skłodowska-Curie COFUND Action, led by Trinity College Dublin on behalf of a group of academic institutions from across Ireland. EDGE will offer 71 prestigious Fellowships for experienced researchers (post-doctoral or equivalent) relocating to Ireland. EDGE is also a training and development programme for scientific excellence, offering a Read more…

Machine Learning

Trinity College Dublin seeks to hire a Professor (Chair) in Intelligent Systems

The University of Dublin, Trinity College, invites applications for the position of Professor of Intelligent Systems. The successful candidate will provide strong academic leadership in research, teaching and supervision. The Professor will strengthen the strategic research areas of Artificial Intelligence and Intelligent Content in the School of Computer Science and Statistics, and provide additional leadership in the SFI Research Centre for Digital Content Technology – ADAPT (www.adaptcentre.ie), hosted in the School. It is essential that the successful candidate will be an internationally recognized scholar in at least one of the following research areas: artificial intelligence; digital media and content analytics; knowledge and data engineering. These areas include scientific areas such as: Machine Learning; Natural Language Processing; Semantic Modelling; Personalisation; Data Read more…

Machine Learning

ParsRec: Meta-Learning Recommendations for Bibliographic Reference Parsing (Pre-Print)

We are delighted to announce that our poster “ParsRec: Meta-Learning Recommendations for Bibliographic Reference Parsing” has been accepted at the 12th ACM Recommender Systems Conference (RecSys) for presentation in Vancouver, Canada. The pre-print is available on arXiv, and here in our blog: Abstract Bibliographic reference parsers extract metadata (e.g. author names, title, year) from bibliographic reference strings. No reference parser consistently gives the best results in every scenario. For instance, one tool may be best in extracting titles, and another tool in extracting author names. In this paper, we address the problem of reference parsing from a recommender-systems perspective. We propose ParsRec, a meta-learning approach that recommends the potentially best parser(s) for a given reference string. We evaluate ParsRec on 105k Read more…

Machine Learning

A Stable Neural-Turing-Machine (NTM) Implementation (Source Code and Pre-Print)

Update 2018-10-20: Official publication available at SpringerLink Update: 2018-10-06: Our paper received the best-paper award at ICANN.   We have released an open source implementation of a Neural Turing Machine for TensorFlow, and published on arXiv the corresponding paper which we will present at ICANN 2018. Neural Turing Machines are notoriously difficult to implement and train. Our contribution is to explain why previous implementations have not successfully replicated the results in the original Neural Turing Machines paper. We then went on and produced an open source implementation which trains reliably and quickly. The work was done as part of my undergraduate thesis in the group of Prof Joeran Beel at the School of Computer Science and Statistics and the ADAPT Centre at Trinity Read more…

Recommender Systems

Mr. DLib’s Living Lab for Scholarly Recommendations (preprint)

We published a manuscript on arXiv about the first living lab for scholarly recommender systems. This lab allows recommender-system researchers to conduct online evaluations of their novel algorithms for scholarly recommendations, i.e., research papers, citations, conferences, research grants etc. Recommendations are delivered through the living lab´s API in platforms such as reference management software and digital libraries. The living lab is built on top of the recommender system as-a-service Mr. DLib. Current partners are the reference management software JabRef and the CORE research team. We present the architecture of Mr. DLib’s living lab as well as usage statistics on the first ten months of operating it. During this time, 970,517 recommendations were delivered with a mean click-through rate of 0.22%. Read more…

Recommender Systems

RARD II: The 2nd Related-Article Recommendation Dataset (preprint)

We released a new version of RARD, i.e. RARD II and describe the new release in a preprint published on arXiv. The dataset is available at http://data.mr-dlib.org and the new manuscript is available on arXiv and here in our Blog. The main contribution of this paper is to introduce and describe a new recommender-systems dataset (RARD II). It is based on data from a recommender-system in the digital library and reference management software domain. As such, it complements datasets from other domains such as books, movies, and music. The RARD II dataset encompasses 89m recommendations, covering an item-space of 24m unique items. RARD II provides a range of rich recommendation data, beyond conventional ratings. For example, in addition to the usual rating Read more…

Partnerships

2-week visit at the NII Tokyo: Dagstuhl-Seminar Presentation, Recommender-System and Machine-Learning Research, …

From the 19th of June until the 2nd of July 2018, I am in Japan at the National Institute of Informatics (NII). It is my first visit as Visiting Professor at the NII, and I am working with Professor Akiko Aizawa on a recommender-system and machine-learning project. Besides that work, there are many interesting presentations and other visitors at the NII. Among others, Prof. Dr. Raimund Seidel is visiting. Prof. Seidel is the organizer of the prestigious Dagstuhl seminar. Dagstuhl enables leading researchers in computer science meet for a few days to discuss the latest advancements and challenges in their fields. The NII is organizing a similar seminar series, the Shonan seminars, and Prof. Seidel shared his experience with organizing the Dagstuhl in a Read more…

Partnerships

MoU between the National Institute of Informatics (NII) and Trinity College Dublin (TCD) / SCSS / ADAPT

After being appointed as a visiting professor at the National Institute of Informatics (NII) a few weeks ago, there is more good news. The NII has signed a memorandum of understanding (MoU) with the School of Computer Science and Statistics (SCSS) of Trinity College Dublin (TCD) and the ADAPT Research Centre. The MoU originates from our long-term collaboration with the NII and outlines a partnership between TCD/SCSS/ADAPT and the NII. The goal of the partnership is to: Engage in joint efforts in research Work together in the area of institute management Exchange administrative and managerial staff Collaborate with industry and agencies for public administration and public services Exchange of research and academic staff and students We begin the collaboration with two projects. First, PhD Read more…

Machine Learning

Aiur by Iris.ai: Solving the Problems of Science via the Blockchain and Artificial Intelligence

I am on the advisory board of Iris.ai, a business start-up in the field of open science, blockchain, and artificial intelligence. Iris.ai was founded in 2015 and since then has released several exciting products that have the potential to revolutionize how scientists work. With their latest project, Project Aiur, the team behind Iris.ai envisions a world where the right scientific knowledge is available at our fingertips; where all research is validated and reproducible; where interdisciplinary connections are the norm; where unbiased scientific information flows freely; where research already paid for with our tax money is freely accessible to all. To realize Project Aiur, Iris.ai sells “AIUR tokens”, a new currency that could be the central currency in a new world of Read more…

Machine Learning

DAAD Artificial Intelligence / Machine Learning Tour Through Germany for Postdocs from Outside Germany

The German Academic Exchange Service (DAAD) organizes the “Postdoctoral Researchers’ Networking AI Tour” 2018 to offer on-site visits to universities, research institutes and companies in the field of artificial intelligence, discussions with experts and numerous networking opportunities. Programme-related costs and a travel allowance are covered by DAAD. We have cooperated and received funding from the DAAD on numerous occasions, e.g. to participate in conferences, receive interns, or conduct research visits abroad e.g. in Cyprus and Tokyo. We were always pleased by the professional organization of DAAD events and great networking opportunities that DAAD offered. As such, we can highly recommend applying for the DAAD Artificial Intelligence Tour through Germany, if you are a postdoc from outside Germany who considers working and living Read more…

Trinity College Dublin (Ireland)

Trinity College Dublin announces a €25 million donation from Naughton Family paving the way for a new €60 million E3 Institute

Trinity College Dublin announced plans for a €60 million new E3 Institute in Engineering, Energy and Environment that has been made possible with a major private philanthropic donation by the Naughton family through the Naughton Foundation, established by the founder of the Glen Dimplex Group, Dr Martin Naughton, and his wife, Carmel. This will be combined with Government funding from the Department of Education and Skills. The Naughton family has made the single largest private philanthropic donation in the history of the state to the new E3 institute by donating €25 million. An additional €15 million is being made available by the Department of Education and Skills. This funding will be provided through the Higher Education Authority (HEA). In addition Read more…

Information Extraction

Machine Learning vs. Rules and Out-of-the-Box vs. Retrained: An Evaluation of Open-Source Bibliographic Reference and Citation Parsers

Our paper “Machine Learning vs. Rules and Out-of-the-Box vs. Retrained: An Evaluation of Open-Source Bibliographic Reference and Citation Parsers” got recently accepted and will be presented at Joint Conference on Digital Libraries 2018. Abstract: Bibliographic reference parsing refers to extracting machine-readable metadata, such as the names of the authors, the title, or journal name, from bibliographic reference strings. Many approaches to this problem have been proposed so far, including regular expressions, knowledge bases and supervised machine learning. Many open source reference parsers based on various algorithms are also available. In this paper, we apply, evaluate and compare ten reference parsing tools in a specific business use case. The tools are Anystyle-Parser, Biblio, CERMINE, Citation, Citation-Parser, GROBID, ParsCit, PDFSSA4MET, Reference Tagger Read more…

Information Extraction

Who Did What? Identifying Author Contributions in Biomedical Publications using Naïve Bayes

Our paper “Who Did What? Identifying Author Contributions in Biomedical Publications using Naïve Bayes” got recently accepted and will be presented at Joint Conference on Digital Libraries 2018. Abstract: Creating scientific publications is a complex process. It is composed of a number of different activities, such as designing the experiments, analyzing the data, and writing the manuscript. Information about the contributions of individual authors of a paper is important for assessing authors’ scientific achievements. Some biomedical publications contain a short section written in natural language, which describes the roles each author played in the process of preparing the article. In this paper, we present a study of authors’ roles commonly appearing in these sections, and propose an algorithm for automatic Read more…

Machine Learning

Call for Marie Curie Individual Fellowships: We are open to supervise projects relating to recommender-systems, machine learning, and NLP here at TCD Dublin

The European Union has published the call for Individual Marie Curie Fellowships (MSCA) with the application deadline being 12 September 2018. The goal of the Individual Fellowships is to enhance the creative and innovative potential of experienced researchers. Our group has already one Marie Curie fellow, i.e. a postdoctoral researcher, as part of the EU/SFI EDGE fellowship programme. However, we are open to supervise more postdoctoral researchers. If you are interested in applying for the Individual Marie Curie Fellowship and need a supervisor, please contact us. We are particularly interested in projects relating to machine learning (machine translation, machine-learning evaluation, novel machine-learning algorithms, curriculum learning), recommender systems, and natural language processing.