Call for Participation DSTC11 – Track4 (Automatic & Robust Dialogue)

November 22nd, 2022 Daniela Lopez de Luise
Track 4: Robust and Multilingual Automatic Evaluation Metrics for Open-Domain Dialogue Systems – Eleventh Dialog System Technology Challenge (DSTC11.T4)

Call for Participation

TRACK GOALS AND DETAILS: Two main goals and tasks:
•    Task 1: Propose and develop effective Automatic Metrics for evaluation of open-domain multilingual dialogs.
•    Task 2: Propose and develop Robust Metrics for dialogue systems trained with back translated and paraphrased dialogs in English.
EXPECTED PROPERTIES OF THE PROPOSED METRICS:
•    High correlation with human annotated assessments.
•    Explainable metrics in terms of the quality of the model-generated responses.
•    Participants can propose their own metric or optionally improve the baseline evaluation metric deep AM-FM (Zhang et al, 2020).

TASK 1: METRICS FOR MULTILINGUAL DATA
In this task, the goal for participants is to propose a single metric model effective for the automatic evaluation of multilingual dialogs in English, Spanish and Chinese. The model will provide scores to obtain high correlations with human-annotations.
Participants are expected to use pre-trained or fine-tune multilingual models and train them to predict multidimensional quality metrics by using self-supervised techniques.
TASK 2: ROBUST METRICS
In this task, the goal for participants is to propose robust metrics for automatic evaluation when dealing with English sentences that have been back translated or automatically paraphrased. Here, robustness is understood when using sentences having the same semantic meaning as the original sentence but different wording.
The proposed metric model will be evaluated when comparing the scores produced on the original sentences w.r.t. with the scores produced when using the back-translated/paraphrased sentences. Therefore, the expected performance must be on par with the correlations with human-annotations obtained over the original sentences.

DATASETS:
For training: Up to 18 Human-Human curated multilingual datasets (+3M turns), with turn/dialogue level automatic annotations including QE metrics or toxicity.
Dev/Test: Up to 10 Human-Chatbot curated multilingual datasets (+150k turns), with turn/dialogue level human annotations.

REGISTRATION AND FURTHER INFORMATION:
ChatEval: https://chateval.org/dstc11
GitHub: https://github.com/Mario-RC/dstc11_track4_robust_multilingual_metrics

PROPOSED SCHEDULE:
Training/Validation data release: From November to December in 2022
Test data release: Middle of March in 2023
Entry submission deadline: Middle of March in 2023
Submission of final results: End of March in 2023
Final result announcement: Early of April in 2023
Paper submission: From March to May in 2023
Workshop: July-September/2023 in a venue to be announced with DSTC11

ORGANIZATIONS:
Universidad Politécnica de Madrid (Spain)
National University of Singapore (Singapore)
Tencent AI Lab (China)
New York University (USA)
Carnegie Mellon University (USA)

Mario Rodríguez Cantelar
Postgraduate Non-Doctoral Researcher / PhD student
Centre for Automation and Robotics (UPM-CSIC)


Read More »

4th Virtual International Conference ICMCSI 2023 12 January 2023 – Tribhuvan University, Nepal

November 18th, 2022 Daniela Lopez de Luise

display this

display this

display this

4th Springer International Conference on Mobile Computing and Sustainable Informatics
[ICMCSI 2023]

ISSN: 2367-4520
Dear Researcher

With a consecutive success in the Scopus-Indexed Publication. We are now back with our next successive  4th Springer International Conference on Mobile Computing and Sustainable Informatics [ICMCSI 2023] organized in association with Tribhuvan University, Nepal on 11-12, Januray 2023. We assure that, the proceedings of conference will be strictly subjected for inclusion into Springer – Lecture Notes on Data Engineering and Communications Technologies [Submitted to Web of Science].

Due to COVID-19, The Conference will be Hosted in ONLINE Mode

All accepted and registered papers of 4th ICMCSI 2023 will be published in Springer LNDECT

[Publication Time: 2 to 3 months from the conference Date]

display this

Series Ed.: Xhafa, Fatos | ISSN: 2367-4512

https://www.springer.com/series/15362

** Indexing:  EI Compendex, INSPEC, Scopus**
All books published in the series are submitted to Web of Science.

ICMCSI Series @ Springer
1st ICMCSI 2020 Publication
2nd ICMCSI 2021 Publication
3rd ICMCSI 2022 Publication

Authors can submit manuscript via Easychair: https://easychair.org/conferences/?conf=icmcsi2023

4th ICMCSI 2023 Conference Brochure

To visit ICMCSI 2023 Conference Website – Click Here

For Queries: +91 8870489968 / icmcsi.conf@gmail.com

display this

Regards

Dr. Subharna Shakya
[Organizing Secretary‐ICMCSI 2023]
Institute of Engineering,
Tribhuvan University,
Nepal.

ICMCSI 2023 Publication Partner
display this

ICMCSI 2023 Organized By
display this

subscribe

Disclaimer: The views and opinions suggested by EJESRA in this email is solely dedicated to research references. Since we are critically-thinking human beings, these views are always subject to change at anytime. So If this message is not relevant to you please forward it to some research community or unsubscribe.

Read More »

Curso “Diseño de Situaciones Educativas”- Virtual con encuentro sincrónicos – actividad sin costo

November 16th, 2022 Daniela Lopez de Luise

Your Ideas Deserve Attention – Make them Known at KES 2023!

November 16th, 2022 Daniela Lopez de Luise

CALL FOR PAPERS – KES 2023

27th International Conference on Knowledge-Based and Intelligent Information & Engineering Systems 

6-8 September 2023 | Athens, Greece

Call for Papers NOW OPEN! Submit your paper today!

Since it's inception 27 years ago, the International Conference on Knowledge-Based and Intelligent Information & Engineering Systems has been the go-to event for exploring intelligent systems and their applications. 

With more over 450 attendees and 5 expert speakers in 2022, the annual KES Conference unites our community to connect, educate, inspire and grow. We are honoured to invite you to submit a paper to share your expertise with our community.

KES-23 will take place in Athens, Greece from 6-8 September 2023. The conference encompasses a broad spectrum of intelligent systems related subjects – the conference scope can be found …here… Below are all of the details and deadlines you need to submit your paper.
Conference Website

HOW TO SUBMIT YOUR PAPER

**DEADLINE TO SUBMIT: 3 April, 2023**

*IMPORTANT* – Full papers should be detailed academic articles in conventional format. (there is no abstract submission stage) The guide length for full papers is 8 to 10 pages (maximum).

DEADLINES FOR SUBMISSIONS

  • Submission of papers Deadline: The deadline to submit your paper is 3 April, 2023.
  • Notification of Acceptance: Your submission will be evaluated by 08 May, 2023.
  • Final Publication Files: Your publication files to be received by 29 May, 2023.

To submit your paper, please click on the following link.
Click Here to Submit your Paper

Scope

General Track Sessions:


G1: Machine Learning, Artificial Neural Networks and Deep Learning

This track will cover both machine learning theoretical research and its applications. Contributions describing machine learning techniques applied to real-world problems and interdisciplinary research involving machine learning in different application fields with especial emphasis on the design of those systems, are particularly encouraged.

G2: Knowledge Based and Expert Systems

This track covers knowledge-based systems and expert systems, both theoretical research and its applications. Contributions using techniques in knowledge-based systems and expert systems applied to real-world problems, as well as interdisciplinary research involving knowledge-based systems and expert systems in different application fields, are particularly encouraged.

G3: Intelligent Information and Engineering Systems

G3 track covers both intelligent information and engineering systems (G3a) and Cybersecurity (G3b), theoretical research and applications. Intelligent information and engineering systems is a broad topic and includes contributions describing techniques handling real-world problems. It also includes research involving intelligent information and engineering in different application fields.

G4: Industry Applications

This track covers Industry Applications. Contributions describing industry application techniques applied to real-world problems and interdisciplinary research involving industry applications in different application fields, with especial emphasis on industry, are particularly encouraged.

 

Call for Invited Sessions

 An invited session consists of a presentation session of 6 to 12 or more papers on a specific conference topic, organised as half or full day mini-conference. We invite senior scientists who have a special interest in a specific conference topic to take responsibility for an invited session, gathering papers from a range of research expertise around the world.  

Researchers who would like to organise one or more Invited Sessions on topics falling within the scope of the conference are invited to submit a proposal for consideration.
Information on Invited Sessions
Information on General Tracks

Submission Guidelines and Review Process

Authors are invited to submit original, unpublished papers which are not under review for another conference, workshop, or journal by the time of submission. The contributors should address one or more research areas included above.

Detailed submission information is available on the conference page 

Read More »

cfp ‘Neurocomputational models of language processing’

November 16th, 2022 Daniela Lopez de Luise

Dear colleagues,

 

could you please be so kind and disseminate the call for papers for the following research topic :

 

Neurocomputational models of language processing

https://www.frontiersin.org/research-topics/49147/neurocomputational-models-of-language-processing

 

Markus J. Hofmann (General and Biological Psychology‪, University of Wuppertal, Germany)

Harm Brouwer (Psycholinguistics, Language Science and Technology, Saarland University, Germany)

Ya-Nin Chang, MRC Cognition and Brain Sciences, University of Cambridge, UK)

Michael Zock (CNRS, AMU, LIS-lab, Marseille, France)

 

Keywords: Neurocomputational Models, Language Processing, Human Neuroscience, Speech and Language, Behavioural Data, Neuroimaging Data, Language Production and Comprehension, Machine Learning, Deep Learning

 

Abstract Submission Deadline : 15 March 2023

Manuscript Submission Deadline 15 November 2023

 

Our ability to produce and understand language involves a complex, dynamic interaction between different types of knowledge, involving orthographic, phonological, semantic, syntactic, and pragmatic representations, as well as knowledge of the world. Moreover, given that discourse rapidly unfolds at the rate of several words per second, these representations need to be activated, retrieved and/or computed in real time. Informed by behavioral and neuroimaging data, explicit neurocomputational models of language processing seek to offer mechanistic explanations of the representations and computations that underlie online language production and comprehension.

 

Neural models from the field of machine learning and particularly deep learning are only the most recent developments in this field. Localist and distributed connectionist models, advanced measurement models like diffusion models, and expert systems are alternative formal approaches able to capture various aspects of language processing. Finally, probabilistic language models as well as corpus-based approaches are powerful computational techniques, which, taken together, may enhance our understanding of language in terms of how it is represented and processed in the human brain.

 

In this Research Topic, we invite submissions that combine such neurocomputational models of language processing with human neuroimaging and behavioral data. The manuscripts can be submitted to Frontiers in Human Neuroscience and may contain sophisticated neural simulations of specific aspects of language processing. These submissions can either deepen our understanding of unimpaired language processing or shed light on language disorders or developmental aspects of language. Alternatively, the papers can be submitted to Frontiers in Artificial Intelligence and thus may highlight the state-of-the-art in natural language processing (NLP). Given this broad spectrum, topics may range from models that seek to explain electrophysiological and functional imaging data to neurally inspired computational models explaining eye-tracking eye-tracking or reading time data. With this special issue, we hope to provide a comprehensive overview of the latest developments in the neurocomputational modelling of human language production and comprehension.

Read More »
« Older Entries
Newer Entries »
Design by 2b Consult