HI4NLP 2020 (co-located at ECAI-2020) - Workshop on Hybrid Intelligence for Natural Language Processing Tasks
*** Updated deadlines following the rescheduling of ECAI 2020 ***
-- Third Call for Papers --
HI4NLP 2020 (co-located at ECAI-2020)
Workshop on Hybrid Intelligence for Natural Language Processing Tasks
August 29, 2020 -- Santiago de Compostela, Galiza/Spain
New deadline for paper submission: May 15, 2020
### Important new dates
* 15 March 15 May 2020 — PAPER submission with Easychair (23:59 UTC-12)
* 15 April 15 June 2020 — Notification of acceptance/rejection
* 29 August 2020 — Workshop day
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.
Topic Areas of Interest: 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):
* Semantic relation extraction (including Open Information Extraction)
* Multi-word expressions discovery and identification
* Named entity recognition and classification
* Event detection and temporal analysis
* Linguistic Analysis
* Dependency parsing
* Discourse analysis
* Argument mining and evaluation
* Grammar checking
* Semantic Models
* (Contextualized) word embeddings
* Distributional semantics and compositionality
* Sentence similarity and paraphrase
* Sentiment analysis
* Hate speech detection
* Rumour and fake news detection
* Authorship attribution
### Related Work using HI in NLP:
* Arcan, Mihael, Marco Turchi, Sara Tonelli, Paul Buitelaar (2017), "Leveraging bilingual terminology to improve machine translation in a CAT environment", Natural Language Engineering, 23(5), pp. 763-788.
* Savary, Agata, Silvio Cordeiro, Carlos Ramisch (2019), "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.
* Gamallo P., Susana Sotelo, J.R. Pichel, Mikel Artetxe. (2019) "Contextualized Translations of Phrasal Verbs with Distributional Compositional Semantics and Monolingual Corpora". Journal of Computational Linguistics, 45(3), pp. 395-421.
* Martín-Rodilla, Patricia, and Cesar Gonzalez-Perez. "An ISO/IEC 24744-derived modelling language for discourse analysis." 2014 IEEE Eighth International Conference on Research Challenges in Information Science (RCIS). IEEE, 2014.
* Vilares, David, Carlos Gómez-Rodriguez and Miguel A. Alonso. “Universal, unsupervised (rule-based), uncovered sentiment analysis.” Knowledge-Based System, volume 118, pp. 45-55, 2017.
* Carlos Gómez, LyS, UDC
* César González, INCIPIT, CSIC
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. Short papers can have up to 3 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:
The proceedings of HI4NLP-2020 will be published by 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 papers will be invited to submit an extended version to 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 Progess 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 and two-day options), and a reduced registration fee for those who also register for the main conference. The registration fees and deadlines will be announced on the ECAI website.
### Program Committee
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
Cesar Gonzalez-Perez, Incipit, CSIC
Nelleke Oostdijk, Radboud University
Thiago Pardo, University of São Paulo
Paulo Quaresma, Universidade de Evora
Carlos Ramisch, Aix Marseille University
Livy Real, IBM
Sara Tonelli, Fondazione Bruno Kessler
Renata Vieira, PUCRS
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
pablo.gamallo at usc.es
### Organizer Committee:
* Pablo Gamallo, CiTIUS, Univ. of Santiago de Compostela
* Marcos Garcia, LyS, Univ. of Corunha
* Patricia Martín-Rodilla, IRlab, Univ. of Corunha
* Martín Pereira, Univ. of Santiago de Compostela -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: text/html Size: 38277 bytes Desc: not available URL: <https://mailman.uib.no/public/corpora/attachments/20200325/9384e1b3/attachment.txt>