Associated Shared tasks
Task 1: Multitask Meme classification - Unraveling Misogynistic and Trolls in Online Memes
Unraveling Misogynistic and Trolls in Online Memes is an Multimodal Machine learning challenge that aims to encourage the development of models for detecting misogynistic memes in Tamil, Malayalam and troll meme in Kannada and Telugu.
The participants will be provided with a training and development datasets. The participants are required to develop models that can analyze the textual and visual components of the memes and predict whether they are misogyny or non-misogyny for Task 1 and troll or not-troll for Task 2. To download the data and participate, go to codalab and click “Participate tab”.
Codalab link: https://codalab.lisn.upsaclay.fr/competitions/16097
Organizers
Bharathi Raja Chakravarthi, School of Computer Science, University of Galway, Ireland
Saranya Rajiakodi, Central University of Tamil Nadu, India
Rahul Ponnusamy, School of Computer Science, University of Galway, Ireland
Kathiravan Pannerselvam, Central University of Tamil Nadu, India
Anand Kumar M, National Institute of Technology Karnataka, India
Student Volunteer:
Hariharan R L, Dept of Information Technology, NITK Surathkal, India
Bhuvaneswari S, Independent researcher, Tamil Nadu, India
Anshid K.A, WMO Imam Gazzali Arts and Science College, Kerala, India
Susminu S Kumar, Revemax pvt ltd, Bangalore, India
Charmathi Rajkumar, The American College, Madurai, Tamil Nadu, India
Task 2: Homophobia/Transphobia Detection in social media comments
Participants Homophobia and Transphobia Detection is the task of identifying homophobia, transphobia, and non-anti-LGBT+ content from YouTube comments. Homophobia and transphobia are both toxic languages directed at LGBTQ+ individuals that are described as hate speech. Although a comment/post in the dataset may contain more than one sentence, the corpus’ average sentence length is one. The corpus includes annotations at the comment/post level.
Participants will be provided with sentences in comments, extracted from social media platforms. Given comments, a system must predict whether or not it contains any form of homophobia/transphobia. The seed data for this task is the Homophobia/Transphobia Detection dataset, a collection of comments from social media. The comments are manually annotated to show whether the text contains homophobia/transphobia.
The participants will be provided development, training and test dataset in English, Hindi, Tamil, Telugu, Kannada, Gujarathi, Malayalam, Marathi and Tulu . To download the data and participate, go to codalab and click “Participate tab”.
Codalab Link: https://codalab.lisn.upsaclay.fr/competitions/16056
Organizers:
Bharathi Raja Chakravarthi, School of Computer Science, University of Galway, Ireland
Ruba Priyadharshini, Gandhigram Rural Institute-Deemed to be university
Prasanna Kumar Kumaresan, Insight SFI Research Centre for Data Analytics, School of Computer Science, University of Galway, Ireland
Paul Buitelaar, Insight SFI Research Centre for Data Analytics, Data Science Institute, University of Galway, Ireland
Asha Hedge, Mangalore University, Mangalore, India
Hosahalli Lakshmaiah Shashirekha, Mangalore University, Mangalore, India
Saranya Rajiakodi, Central University of Tamil Nadu, India
Miguel Ángel García-Cumbreras, Universidad de Jaén, Spain
Salud María Jiménez-Zafra, Universidad de Jaén, Spain
José Antonio García-Díaz, Universidad de Murcia, Spain
Rafael Valencia-García, Universidad de Murcia, Spain
Student Volunteer:
Kishore Kumar Ponnusamy, Digital University of Kerala, India
Poorvi Shetty
Daniel García-Baena, Universidad de Jaén, Spain
Task 3: Speech Recognition for Vulnerable Individuals in Tamil
This shared task addresses a challenging area in Automatic Speech Recognition: vulnerable old-aged and transgender people in Tamil. People in their old-age visit primary locations such as banks, hospitals and administrative offices to address their needs in their quotidian lives. Many aged people are unaware of using the equipment facilitated to aid people. Similarly, transgender people are deprived of primary education because of prejudice in society, so speech is the only medium that could assist them in satisfying their needs. The spontaneous speech data is gathered from old-aged and transgender people, who are bereft of using these facilities to their advantage. The speech corpus containing 5.5 hours of transcribed speech will be released for the training set, and 2 hours of speech data will be released for testing.
Codalab Link: https://codalab.lisn.upsaclay.fr/competitions/16094
Organizers:
Bharathi B, Sri Sivasubramaniya Nadar College of Engineering, Chennai.
Bharathi Raja Chakravarthi, School of Computer Science, University of Galway, Ireland
Sripriya N, Sri Sivasubramaniya Nadar College of Engineering, Chennai.
Rajeswari Natarajan, SASTRA University, Tamil Nadu, India
Student Volunteer:
Suhasini S, Sri Sivasubramaniya Nadar College Of Engineering, Chennai.
Task 4: Caste/migration Hate Speech Detection
The shared task on Caste/migration hate speech detection is a text classification task that aims to encourage the development of models for detecting the caste/migration hate speech texts. The main objective of this task is to create an automatic classification system that predicts whether the text contains caste/migration hate speech or not on social media. The participants will be provided with training, development, and test datasets in Tamil. As far as we know, this is the first shared task on Caste/migration hate speech detection. For more information, please click the below Codalab competition link.
Codalab Link: https://codalab.lisn.upsaclay.fr/competitions/16089
Organizers:
Saranya Rajiakodi, Central University of Tamil Nadu, India
Bharathi Raja Chakravarthi, School of Computer Science, University of Galway, Ireland
Rahul Ponnusamy, School of Computer Science, University of Galway, Ireland
Prasanna Kumar Kumaresan, School of Computer Science, University of Galway, Ireland
Sathiyaraj Thangasamy, Department of Tamil, Sri Krishna Adithya College of Arts and Science, Tamil Nadu, India
Bhuvaneswari Sivagnanam, Central University of Tamil Nadu, India
Student Volunteer:
Charmathi Rajkumar, The American College, Madurai, Tamil Nadu, India
Task 5: Shared task on Stress Identification in Dravidian Languages
Stress is an emotional state. It can be triggered by any circumstance or idea that gives cause for annoyance, rage, or anxiety. Identifying stress early and addressing it well are crucial. Otherwise, stress might also additionally result in depression. This shared task aims to detect whether a person is affected by stress from their social media postings wherein people share their feelings and emotions. Given social media postings in Tamil and Telugu code-mixed languages, the system should classify into two labels namely “stressed” or “not stressed
Codalab Link: https://codalab.lisn.upsaclay.fr/competitions/16092
Organizers:
Kayalvizhi Sampath, Jeppiaar University, Chennai.
Thenmozhi Durairaj, Sri Sivasubramaniya Nadar College Of Engineering, Chennai.
Jerin Mahibha C, Meenakshi Sundararajan Engineering College, Chennai.
Student Volunteer:
Ramya Priya S. Sri Sivasubramaniya Nadar College Of Engineering, Chennai
Bharani kasinathan, School of Engineering and Technology, Jeppiaar University,Chennai.
Important Dates for shared tasks:
Task announcement: October 15, 2023
Release of Training data: October 20, 2023
Release of Test data: November 15, 2023
Run submission deadline: November 25, 2023
Results declared: December 1, 2023
Paper submission: December 18, 2023
Peer review notification: January 20, 2024
Camera-ready paper due: January 30, 2024
Workshop Dates: March 21-22, 2024