HI4NLP
Workshop on Hybrid Intelligence for Natural Language Processing Tasks (co-located at ECAI-2020)
June 8 RESCHEDULED August 29, 2020 Santiago de Compostela, Galicia, Spain
Workshop on Hybrid Intelligence for Natural Language Processing Tasks (co-located at ECAI-2020)
June 8 RESCHEDULED August 29, 2020 Santiago de Compostela, Galicia, Spain
There have been spectacular advances in many tasks of natural language processing (NLP) by making use of artificial intelligence (IA) techniques such as machine/deep learning (M/DL). However, these improvements do not affect all NLP tasks, specifically those that require deep linguistic knowledge, natural language understanding, semantic inference and reasoning. In hybrid architectures, M/DL approaches co-exist with symbol-manipulation as symbolic models seem to play an important role in inference and reasoning about abstract knowledge.
We call hybrid intelligence (HI) those architectures that integrate symbolic information into statistical or neural-based models so as to allow machines to learn new knowledge in a more 'intelligent' way by endowing them with common sense and deep understanding. The main aim of HI in NLP is to inject deep and structured linguistic knowledge (not just annotated text) into M/DL models so as to develop hybrid architectures for NLP tasks. In more general terms, the concept of HI consists of combining machine and human intelligence to overcome the shortcomings of existing AI systems. Abstract and structured knowledge from specialists can be used not just as training data to learn uninterpretable black-box models, but also to design the models themselves by making them more transparent, easy to interpret by humans, and more efficient for specific purposes.
HI4NLP will provide a forum for discussing about exciting research on HI methodology for NLP tasks. It is open to any contribution that requires deep semantic analysis, such as semantic relation extraction, discourse analysis, argument mining, rumour detection, and so on. Strategies can combine statistical or neural-based models with symbolic information based on propositions, regular patterns, rules, or whatever language resource aimed at representing abstract and structured knowledge.
HI4NLP should interest researchers working on the following topics and sub-topics of NLP by making use of HI approaches (the list is not exhaustive):
Submissions should describe original, unpublished work. Authors are invited to submit two kinds of papers:
Full papers – Reporting substantial and completed work, especially those that may contribute in a significant way to the advancement of the area. Wherever appropriate, concrete evaluation results should be included. Full papers can have up to 8 content pages (without references).
Short papers - Reporting small, focused contributions such as ongoing work, position papers, potential ideas to be discussed, negative results, or an interesting application nugget. Short papers can have up to 4 content pages + 1 page for references.
Each submission will be evaluated by at least three reviewers. As usual for the main ECAI conference, submissions are NOT anonymous. According to the template, names of authors should be stated in the manuscript.
Submissions should be written in English. At submission time, only PDF format is accepted. For the final versions, authors of accepted papers will be given 1 extra content page to take the reviews into account. Authors of accepted papers will be requested to send the source files for the production of the proceedings.
All submitted papers must conform to ECAI stylesheet
Submission and review of papers for HI4NLP 2020 will be managed via Easychair
PUBLICATION
The proceedings of HI4NLP-2020 will be published via CEUR. They will be available online. To ensure publication, at least one author of each accepted paper must complete a full registration at the Workshop.
SELECTED PAPER PUBLICATION
Selected papers will be invited to submit an extended version in the following journals:
Best paper to a Special Issue of the International Journal of Interactive Multimedia and Artificial Intelligence , to be published in 2021 (this year, Clarivate Analytics has accepted the inclusion of IJIMAI in the JCR)
Second best paper to a Special Issue of Progress in Artificial Intelligence , indexed by SJR.
REGISTRATION AND PARTICIPATION
Every workshop participant must register for the ECAI workshop program. Workshop registration will include workshop attendance, lunch, and coffee-breaks
There will be "Workshop-only" registration (one-day or two-day options), and a reduced registration fee for those who also register for the main conference. The registration fees and deadlines will announced on the ECAI website.
Leveraging bilingual terminology to improve machine translation in a CAT environment
Natural Language Engineering, 23(5), pp. 763-788
Without lexicons, multiword expression identification will never fly: A position statement
Proceedings of the Joint Workshop on Multiword Expressions and WordNet (MWE-WN 2019), Florence, Italy
Contextualized Translations of Phrasal Verbs with Distributional Compositional Semantics and Monolingual Corpora
Journal of Computational Linguistics, 45(3), pp. 395-421.
An ISO/IEC 24744-derived modelling language for discourse analysis
IEEE Eighth International Conference on Research Challenges in Information Science (RCIS), pp. 1-10, ISBN 978-1-4799-2393-9
Universal, unsupervised (rule-based), uncovered sentiment analysis
Knowledge-Based System, volume 118, pp. 45-55 ISSN 0950-7051
LyS Group, University of A Corunha (UDC) Associate Profesor
ERC Starting Grant by the European Research Council, project FASTPARSE (Fast Natural Language Processing for Large-Scale NLP).
Incipit- CSIC, Spanish National Research Council Staff Scientist
Leader of a co-research line on Software Engineering and Cultural Heritage, with special interest on Language and Knowledge conexions.
Agenda in Santiago de Compostela local summer time (GMT+2)
Miguel A. Alonso, Universidade da Coruña, Centro de Investigación CITIC
Daniela Claro, FORMAS/LASID/DCC/UFBA
Luísa Coheur, IST/INESC-ID Lisboa
Gaël Dias, Normandie University
César González-Pérez, Incipit, CSIC
Nelleke Oostdijk, Radboud University
Thiago Pardo, University of São Paulo
Paulo Quaresma, Universidade de Évora
Carlos Ramisch, Aix Marseille University
Livy Real, IBM
Sara Tonelli, Fondazione Bruno Kessler
Renata Vieira, PUCRS, Brazil
Jesús Vilares, Universidade da Coruña, Centro de Investigación CITIC
Manuel Vilares Ferro, University of Vigo
Aline Villavicencio, University of Sheffield and Federal University of Rio Grande do Sul
Arkaitz Zubiaga, Queen Mary University of London
