Welcome to the ARTIFICIAL INTELLIGENCE for QUESTION ANSWERING Workshop

Call for Papers Submit your Paper

Call for Papers

1st International Workshop
ARTIFICIAL INTELLIGENCE for QUESTION ANSWERING (AIQA2018)

Budapest, Hungary
September 2, 2018

In conjunction with the 22nd European Conference on
Advances in Databases and Information Systems (ADBIS 2018)

WORKSHOP OVERVIEW

Artificial Intelligence (AI) is attracting much attention and it will be a major driver of technology in the coming years. It will bring a big transformation to many industries, such as transportation, manufacturing, healthcare, communications, financial services, and more. This is possible because of the big data availability, the advances in hardware capabilities and the inventions of new models, methods, algorithms capable to offer new solutions for long-standing research problems.

Question Answering (QA) is a complex task that requires the ability to understand the natural language (NLU) and to reason over relevant contexts. Almost all Natural Language Processing (NLP) tasks can be seen as QA problem (e.g. entity extraction, sentiment analysis, machine translation).

Recently, QA by using novel AI techniques has seen scientific and commercial popularity that attracted media attention, but effective QA is a challenging task for machines that try to simulate the human behaviour.
Some solutions are based on Information Retrieval (IR) techniques, other on Information Extraction (IE) processes that enable to create Knowledge Bases (KBs), so logic-based query languages are used to infer answers from KBs. KB-based solutions can be satisfactory for closed-domain problems, but they are unlikely to scale up to answer questions on any topic. Novel approaches for QA over documents are based on Deep Neural Networks that encode the documents and the questions to determine the answers. A lot of research has focused on learning from fixed training sets of labeled data, but other try to learn through online interaction (dialogue) with humans or other agents. This is the case of conversational agents (or conversational interfaces/bots/chatbots) that adapt their model based on teacher's feedbacks (Reinforcement Learning) and change beliefs in response to new information.

The purpose of the AI*QA 2018 workshop is to bring together researchers, engineers, and practitioners interested in the theory and applications related to the Question Answering (QA) problem by using Artificial Intelligence (AI) techniques. The aim is to better understand the advantages and the limitations of proposed solutions and systems in different domains and situations by stimulating and facilitating through the workshop an active exchange, interaction, and comparison of approaches, methods, tools, and ideas.

TOPICS OF INTEREST

Topics of interest include but are not limited to:

  • Theoretical models for answering questions
    • Rule-based models
    • Logic-based models
    • IR-based models
    • Probabilistic models
    • Graph-based models
    • Deep Learning models
    • Reinforcement‐based Learning models
    • Belief‐based Learning Models
    • Hybrid models
  • Algorithms and methods
    • Improving the learning process through dialogue interactions for natural language comprehension: human in the loop, reinforcement learning, conversational agents or bots
    • Reasoning on KBs to help infer answers to complex questions: knowledge representation and reasoning, logical agents
    • Information Extraction, Information Retrieval, and Semantic Search and Labeling to enable answering of questions
    • Hybrid Methods for implementing solutions that enable to answer questions
  • Databases and knowledge representations
    • Knowledge Bases (KBs): answering questions by exploiting KBs
    • Document / raw text: natural language comprehension and question answering
    • Hybrid Databases as sources exploited for answering questions
    • Ontologies that provides a common vocabulary used to state facts and formulate questions about the domain
  • Tools and solutions
    • Deep Insight Engines that exploit question answering techniques
    • Frameworks to validate results in question answering
    • Social bots able to automatically produce responses through natural language algorithms
    • Question answering systems that integrate different modules, also exploiting existing tools
    • User interfaces for simplifying human-machine interaction and answering questions
    • Conversational interfaces implemented, for instance, by Natural Language Understanding services
  • Evaluation of results
    • Evaluation measures of the quality of the answers
    • Experiment design: planning a study to meet specified objectives in Question Answering solutions
    • Overview/Survey: Classification and/or Comparison of approaches related to the question answering problem
    • Empirical evaluation algorithms or systems for Question Answering
    • Evaluation of Natural Language Understanding services for (conversational) Question Answering Systems
    • Corpus and Ground-Truth construction, and their publication for problems related to the evaluation of question answering approaches
  • Application to domains
    • AI techniques applied to solve Question Answering problems or to implement chatbots applied in different areas of, but not limited to: finance, marketing, e-commerce, health care, transportation, internet of things, tourism. Can be presented needs, proposed solutions, case studies, benefits and related experiences

PROGRAM

September 2, 2018

  • 10:30 - 11:00    Coffee break
  • 11:00                 Welcome
  • 11:05 - 12:15    Keynote: "Talking to Machines: A Conversational Journey"
    • Abstract: Talking to machines is not evoking science fiction scenes as it used to be in the sixties or even the nineties, anymore. In the last fifty years, we have explored the space of human-computer communications via speech, text, touch and multimodal input and output. We now have computers in various forms sitting in our living room ready to take on new social roles. Wearable computers may interject in our daily routine and persuade us to healthy behaviour. In this talk, we will review what is the current state-of-the-art in modelling the human-machine conversational dialogue and the many challenges ahead.
    • Author: Prof. Giuseppe Riccardi, University of Trento, Italy
  • 12:15 - 13:25    Technical Session
    • "Towards Multilingual Neural Question Answering"
      Ekaterina Loginova, Stalin Varanasi, and Gunter Neumann (DFKI, Saarbrucken, Germany)
    • "Knowledge Base Relation Detection via Multi-View Matching"
      Yang Yu (IBM Watson, USA), Kazi Saidul Hasan (IBM Watson, USA), Mo Yu (AI Foundations, IBM Research, USA), Wei Zhang (AI Foundations, IBM Research, USA), and Zhiguo Wang (IBM Research, USA)
    • "Analysis of Why-type Questions for the Question Answering System"
      Manvi Breja and Sanjay Kumar Jain (National Institute of Technology, Kurukshetra, Haryana, India)
  • 13:25                 Conclusions
  • 13:30 - 14:30    Lunch

IMPORTANT DATES

For any question, please, conctact us

  • Regular Paper Submission: (Extended) May 16, 2018
  • Short and Position Paper Submission: (Extended) June 06, 2018
  • Regular Paper Acceptance Notification: June 06 2018
  • Short and Position Paper Acceptance Notification: June 11 2018
  • Camera-ready Submission: June 18, 2018
  • Workshop: September 02, 2018

SUBMISSION GUIDELINES

Submission link: https://easychair.org/conferences/?conf=aiqa2018

Authors are invited to submit electronically original contributions in English, carefully checked for correct grammar and spelling, addressing one or several topics of interest. Each paper should clearly indicate the nature of its main contribution. Work in progress or discussion about ideas, methods, and initial experimental results are also welcome.

  • Regular papers: Camera-ready length is limited to 12 pages.
  • Short papers / Position papers / Demos / Work in progress: Camera-ready length is limited to 8 pages.

Camera-ready version & Copyright Form

PUBLICATION

  • AI*QA 2018 proceedings will be published in Springer’s Communications in Computer and Information Science (Springer) series.
  • We plan to invite selected workshop papers for publication in an international journal.
  • At least one author of each accepted paper must register and attend the workshop to present the paper.

COMMITTEES

Workshop Co-Chairs

  • Ermelinda Oro (National Research Council, Italy)
  • Massimo Ruffolo (National Research Council, Italy)
  • Eduardo Fermè (University of Madeira, Portugal)

Program Committee

  • Muhammad Arif (University of Malaya, Malaysia)
  • Alexandra Balahur (European Commission Joint Research Centre, Italy)
  • Ioannis Hatzilygeroudis (University of Patras, Greece)
  • Ivan Jureta (University of Namur, Belgium)
  • Joohyung Lee (Arizona State University, Arizona, USA)
  • Marco Leo (Institute of Optics, CNR, Italy)
  • Yuan-Fang Li (Monash University, Australia)
  • Olga Kalimullina (National Research University ITMO, Russia)
  • Thomas Meyer (University of Cape Town and CAIR, South Africa)
  • Guenter Neumann (German Research Center for Artificial Intelligence, DFKI, Germany)
  • Rafael Peñaloza (Free University of Bozen-Bolzano, Italy)
  • David Schlangen (Bielefeld University, Germany)
  • Koichi Takeda (Nagoya University, Japan)
  • Wei Zhang (IBM Research AI, NY, USA)

INVITED SPEAKER

Prof. Giuseppe Riccardi

University of Trento, Italy
_____
Prof. Giuseppe Riccardi is founder and director of the Signals and Interactive Systems Lab at University of Trento, Italy. He received his Laurea degree in Electrical Engineering and Master in Information Technology, in 1991, from the University of Padua and CEFRIEL/Politechnic of Milan (Italy), respectively. From 1990 to 1993 he collaborated with Alcatel-Telettra Research Laboratories (Italy). In 1995 he received his PhD in Electrical Engineering from the Department of Electrical Engineering at the University of Padua, Italy. From 1993 to 2005, he was at AT&T Bell Laboratories (USA) and then AT&T Labs-Research (USA) where he worked in the Speech and Language Processing Lab. In 2005 joined the faculty of University of Trento (Italy). He is affiliated with the Department of Information Engineering.
Prof. Riccardi's research on stochastic finite state machines for speech and language processing has been applied to a wide range of domains for task automation. He and his colleagues designed the AT&T spoken language system ranked first in the 1994 DARPA ATIS evaluation. He and his colleagues pioneered the speech and language research in spontaneous speech for the well-known "How May I Help You?" research program which led to breakthrough speech services. His research on learning finite state automata and transducers has lead to the creation of the first large scale finite state chain decoding for machine translation (Anuvaad). He lead University of Trento’s team that contributed to the IBM WATSON machine that won the Jeopardy! challenge.
Prof. Riccardi has co-authored more than 200 scientific papers. He holds more than 70 patents in the field of automatic speech recognition, understanding, machine translation, natural language processing and machine learning. His current research interests are natural language modeling and understanding, spoken/multimodal dialogue, affective computing, machine learning and social computing.
Prof. Riccardi has been on the scientific and organizing committee of EUROSPEECH, INTERSPEECH, ICASSP, NAACL, EMNLP, ACL an EACL. He has co-organized the IEEE ASRU Workshop in 1993, 1999, 2001 and General Chair in 2009. He has been the Guest Editor of the IEEE Special Issue on Speech-to-Speech Machine Translation. He has been a founder and Editorial Board member of the ACM Transactions of Speech and Language Processing. He has been elected member of the IEEE SPS Speech Technical Committee (2005-2008). He is member of ACL, ACM and elected Fellow of IEEE (2010) and of ISCA (2017).
Prof. Riccardi has received many national and international awards including the Marie Curie Excellence Grant (predecessor of the ERC Starting Grant ) by the European Commission, IEEE SPS Best Paper Award, IBM Faculty Award and AMAZON Alexa award.

VENUE

The conference will be held in Danubius Hotel Flamenco **** , Wellness and conference hotel Budapest, Hungary

Address: Budapest, Tas vezér u. 3-7, 1113

https://www.danubiushotels.com/en/our-hotels-budapest/danubius-hotel-flamenco

For any question, please, conctact us

SPONSORS & SUPPORTERS

ICAR-CNR

Institute for high performance computing and networking National Research Council https://www.icar.cnr.it/en/

Altilia srl

a Machine Intelligence company www.altiliagroup.com

CONTACT US

If you have any further question or information request on AI*QA 2018 workshop, please, contact us:

send an email to: linda.oro@icar.cnr.it

follow us: @AIQA2018