Dear all, Apologies for cross-posting. you are requested to please circulate it for wider publicity... ....................................................................................................................................
6th Workshop on Indian Language Data: Resources and Evaluation (WILDRE) <http://sanskrit.jnu.ac.in/conf/wildre6> Date: Monday, 20th June 2022 (afternoon session) Venue: Palais du Pharo, Marseille, France (Organized under LREC 2022 (20-25 June 2022) <https://lrec2022.lrec-conf.org/en/>) *Deadline extension: 18 April 2022* Website: http://sanskrit.jnu.ac.in/conf/wildre <http://sanskrit.jnu.ac.in/conf/wildre6>6 WILDRE-6, the 6th Workshop on Indian Language Data: Resources and Evaluation is proposed to be organized in Marseille (France) on 20th June 2022 under the LREC platform. India has a huge linguistic diversity and has seen concerted efforts from the Indian government and industry for developing language resources. European Language Resource Association (ELRA) and its associate organizations have been very active and successful in addressing the challenges and opportunities related to language resource creation and evaluation. It is therefore a big opportunity for resource creators of Indian languages to showcase their work on this platform and also to interact and learn from those involved in similar initiatives all over the world. The broader objectives of the WILDRE will be - To map the status of Indian Language Resources - To investigate challenges related to creating and sharing various levels of language resources - To promote a dialogue between language resource developers and users - To provide an opportunity for researchers from India to collaborate with researchers from other parts of the world Dates for Short/Long papers and Posters and Demos *April 18, 2022*: Paper submissions due May 03, 2022: Paper notification acceptance May 23, 2022: Camera-ready papers due June 20, 2022: Workshop SUBMISSIONS Papers must describe original, completed/ in progress and unpublished work. Each submission will be reviewed by three program committee members. Accepted papers will be given up to 10 pages (for full papers) 5 pages (for short papers and posters) in the workshop proceedings, and will be presented as oral papers or posters. Papers should be formatted according to the LREC style-sheet, which is provided on the LREC 2022 website ( http://lrec2022.lrec-conf.org/en/submission/authors-kit/). Please submit papers in PDF format to the LREC website <https://www.softconf.com/lrec2022/WILDRE-6/>. We are seeking submissions under the following category - Full papers (10 pages) - Short papers (work in progress: 5 pages) - Posters (innovative ideas/proposals, research proposals of students) - Demo (of working online/standalone systems) WILDRE-6 will have a special focus on Demos of Indian Language Technology. In the past few years, as more resources have been developed and made available, there has been increased activity in developing usable technology using these. WILDRE-6 would like to encourage and widen the Demo track to allow the community to showcase their demos and have mutually beneficial interactions with each other as well as resource developers. WILDRE-6 is seeking full, short papers, posters and demos on the following topics related to Indian Language Resources: - Digital Humanities, heritage computing - Corpora - text, speech, multimodal, methodologies, annotation and tools - Lexicons and Machine-readable dictionaries - Ontologies, Grammars - Language resources for NLP/ IR/Speech tasks, tools and Infrastructure for language resources - Standards or specifications for language resources application - Licensing and copyright issues - Data mining - Text summarization Both submission and review processes will be handled electronically. The review process will be double-blind. The workshop website will provide the submission guidelines and the link for the electronic submission. When submitting a paper from the START page, authors will be asked to provide essential information about resources (in a broad sense, i.e. also technologies, standards, evaluation kits, etc.) that have been used for the work described in the paper or are a new result of your research. Moreover, ELRA encourages all LREC authors to share the described LRs (data, tools, services, etc.), to enable their reuse, replicability of experiments, including evaluation ones, etc. For further information on this initiative, please refer to http://lrec2022.lrec-conf.org/en *Shared Tasks:* The Sixth Workshop on Indian Language Data: Resources and Evaluation (WILDRE -6) <http://sanskrit.jnu.ac.in/conf/wildre6/index.jsp> at LREC-2022 will include two shared tasks on (a) Speech Technologies for Under-resourced Indian Languages (SpeechTech-IL) and (b) Universal Dependency based Morpho-Syntactic Parsing in Indian Languages (UDParse-IL). (a) Speech Technologies for Under-resourced Indian Languages (SpeechTech-IL) Neural or deep learning techniques are currently being applied in state-of-the-art automated systems that report significant performance improvements, but typically require a large amount of high-quality data. However, in order to advance Automatic Speech Recognition (ASR) and Text-to-Speech (TTS) systems for low resource languages, the zero-shot/unsupervised approach is one notable development in Neural learning that builds ASR/TTS systems for languages where the size of audio and/or transcribed speech data may be small or even non-existent. In this shared task, we will solicit participants to submit novel zero-shot (or similar methods) and/or linguistically-encoded features systems for under-resourced Indian languages. The goal will be to ascertain the effectiveness of the method implemented for language pairs as well as for unseen similar languages. The languages are Hindi, Odia, Marathi and Bhojpuri. In evaluation, participants will also get 2/3 surprise tests for closely-related languages. The system(s) will be evaluated using WER, precision, recall and F-score. (b) Universal Dependency based Morpho-Syntactic Parsing in Indian Languages (UDParse-IL) The primary objective of the UDParse-IL task is to find notable techniques for developing universal dependency parsers, especially when a language is low-resourced. In this task, the participants will be provided with training, development and testing datasets annotated with dependency relations in 10 Indian Languages - Bhojpuri, Hindi (including Hindi-English code switched), Marathi, Sanskrit, Tamil, Telugu, Urdu, Punjabi, and Magahi - and we will solicit participants to submit systems based on novel zero/few-shot (or other cross-lingual and multilingual) similar methods for these low-resource Indian languages. All the languages included in this task, with the exception of Hindi and Urdu, don’t have more than 1,350 annotated sentences. The data of the first nine languages mentioned above will be shared by UFAL, Charles University from the Universal Dependencies (UD) repositories. We will provide test data and an evaluation platform to evaluate the participant's developed parsers. The parsers will be evaluated using LAS, UAS, precision, recall and F-score. One of the primary goals of the task is to ascertain the effectiveness of the implemented methods for unseen but closely-related languages, in addition to the languages for which the training dataset is being provided. In order to do this, the test data will include some surprise languages - the names of these surprise/unseen test languages will be revealed at the test time itself and a test set for these languages will be provided. Shard Task Dates Jan 31, 2022: Registration <https://forms.gle/B4ha4z4FtReuHrCS8> Feb 09, 2022: Train and Validation Data set Release April 15, 2022: Test Set Release March 24, 2022: System Submission Due April 08, 2022: System Results April 18, 2022: System Description Paper Due May 03, 2022: Paper notification of acceptance May 23, 2022: Camera-ready papers due Workshop Chairs - Girish Nath Jha, Jawaharlal Nehru University, India - Kalika Bali, Microsoft Research India Lab, Bangalore, India - Sobha L, AU-KBC, Anna University, Chennai, India Workshop Organizing Committee - Girish Nath Jha, Jawaharlal Nehru University, India - Kalika Bali, Microsoft Research India Lab, Bangalore, India - Sobha L, AU-KBC, Anna University, Chennai, India - Atul Kr. Ojha, National University of Ireland, Galway, Ireland & Panlingua Language Processing LLP, India Shared Task Organizers Atul Kr. Ojha, NUI Galway, Ireland and Panlingua Language Processing LLP Aryaman Arora, Georgetown University Akanksha Bansal, Panlingua Language Processing LLP Esha Banerjee, Google USA Ritesh Kumar, Agra University Girish Nath Jha, JNU, New Delhi, India Kalika Bali, Microsoft Research India Manu Chopra, Karya Inc. Sobha L., AU-KBC, India Sourabrta Mukherjee, Panlingua Language Processing LLP & Charles University, Prague Swapnil, Goa University, Goa Vivek Sheshadri, MSR, India Program Committee (to be updated) - Adil Amin Kak, Kashmir University - Anil Kumar Singh, IIT BHU, Benaras - Anupam Basu, Director, NIIT, Durgapur - Anoop Kunchukuttan, Microsoft AI and Research, India - Arul Mozhi, University of Hyderabad - Asif Iqbal, IIT Patna, Patna - Atul Kr. Ojha, National University of Ireland Galway, Ireland & Panlingua Language Processing LLP, India - Bharathi Raja Asoka Chakravarthi, National University of Ireland Galway, Ireland - Bogdan Babych, Heidelberg University, Germany - Chao-Hong Liu, Potamu Research Ltd., Ireland - Claudia Soria, CNR-ILC, Italy - Dafydd Gibbon, Universität Bielefeld, Germany - Daan van Esch, Google, USA - Dan Zeman, Charles University, Prague, Czech Republic - Delyth Prys, Bangor University, UK - Dipti Mishra Sharma, IIIT, Hyderabad - Diwakr Mishra, Amazon-Bangalore, India - Dorothee Beermann, Norwegian University of Science and Technology (NTNU) - Elizabeth Sherley, IIITM-Kerala, Trivandrum - Esha Banerjee, Google, USA - Eveline Wandl-Vogt, Austrian Academy of Sciences, Austria - Georg Rehm, DFKI, Germany - Girish Nath Jha, Jawaharlal Nehru University, New Delhi - Jan Odijk, Utrecht University, The Netherlands - John P. McCrae, National University of Ireland Galway, Ireland - Jolanta Bachan, Adam Mickiewicz University, Poland - Joseph Mariani, LIMSI-CNRS, France - Jyoti D. Pawar, Goa University - Kalika Bali, MSRI, Bangalore - Khalid Choukri, ELRA, France - Lars Hellan, NTNU, Norway - M J Warsi, Aligarh Muslim University, India - Malhar Kulkarni, IIT Mumbai - Manji Bhadra, Bankura University, West Bengal - Marko Tadic, Croatian Academy of Sciences and Arts, Croatia - Massimo Monaglia, University of Florence, Italy - Monojit Choudhary, MSRI Bangalore - Narayan Choudhary, CIIL, Mysore - Nicoletta Calzolari, ILC-CNR, Pisa, Italy - Niladri Shekhar Dash, ISI Kolkata - Panchanan Mohanty, GLA, Mathura - Pinky Nainwani, Cognizant Technology Solutions, Bangalore - Pushpak Bhattacharya, IIT Mumbai - Rajeev R R, ICFOSS, Trivandrumv - Ritesh Kumar, Agra University - Shantipriya Parida, Silo AI - Vijay Kumar, TDIL, MEITY, Govt of India - S.S. Agrawal, KIIT, Gurgaon, India - Sachin Kumar, EZDI, Ahmedabad - Santanu Chaudhury, Director, IIT Jodhpur - Shivaji Bandhopadhyay, Director, NIT, Silchar - Sobha L, AU-KBC Research Centre, Anna University - Stelios Piperidis, ILSP, Greece - Subhash Chandra, Delhi University - Swaran Lata, TDIL, MCIT, Govt of India - Virach Sornlertlamvanich, Thammasat University, Bangkok, Thailand - Vishal Goyal, Punjabi University, Patiala - Zygmunt Vetulani, Adam Mickiewicz University, Poland Workshop contact: - For questions related to shared tasks (a) and (b), please send an email to wildre-speechtec...@googlegroups.com and wildre -udpars...@googlegroups.com respectively. For urgent/specific queries on the workshop or shared tasks please contact Atul Kr. Ojha at atulkumar.o...@insight-centre.org Identify, Describe and Share your LRs Describing your LRs in the LRE Map is now a normal practice in the submission procedure of LREC (introduced in 2010 and adopted by other conferences). To continue the efforts initiated at LREC 2014 about “Sharing LRs” (data, tools, web services, etc.), authors will have the possibility, when submitting a paper, to upload LRs in a special LREC repository. This effort of sharing LRs, linked to the LRE Map for their description, may become a new “regular” feature for conferences in our field, thus contributing to creating a common repository where everyone can deposit and share data. As scientific work requires accurate citations of referenced work so as to allow the community to understand the whole context and also replicate the experiments conducted by other researchers, LREC 2022 endorses the need to uniquely Identify LRs through the use of the International Standard Language Resource Number (ISLRN, www.islrn.org), a Persistent Unique Identifier to be assigned to each Language Resource. The assignment of ISLRNs to LRs cited in LREC papers will be offered at submission time.
_______________________________________________ Moses-support mailing list Moses-support@mit.edu https://mailman.mit.edu/mailman/listinfo/moses-support
