Second Workshop on Multimodal Machine Learning in Low-Resource Languages

We are pleased to announce our Second Workshop on Multimodal Machine Learning in Low-Resource Languages (MMLow 2023), a cutting-edge event that aims to explore the intersection of multimodal learning and low-resource languages. Following the success and achievements of our First workshop (MMLow 2022) in ICON(International Conference on Natural Language Processing 2022) held at IIIT Delhi, this tagged event serves as a seamless continuation of our exploration into the dynamic field of multimodal machine learning and its application to low-resource languages. Our aim is to further delve into the challenges involved in bridging the gap between multimodal learning and low-resource languages, as well as to investigate cutting-edge solutions that might result in more inclusive and efficient language technology. We continue to build a vibrant and encouraging community by building on the discussion and research from the prior workshop. By bringing together scholars, practitioners, researchers, and enthusiasts, we are able to extend the boundaries of AI and contribute to the betterment of linguistic diversity and understanding.

Due to the fast growth of data, we have seen a considerable increase in the use of Natural Language Processing and Computer Vision applications in the current setting. However, these developments have mainly focused on visual tasks because there weren't as many labeled samples available across the other modalities. When algorithms are independently trained on various modalities, there is a huge performance gap, as there are many large labeled datasets for images but not for audio or video data. To cater to this need, Researchers and Professionals are increasingly focusing on the field of multimodal machine learning. Multimodal machine learning aims to close such research gaps and maximize the potential of various data sources by utilizing the strength of several modalities, such as language, audio, and visual data. By exploring the challenges and exploring multimodal machine learning techniques, the workshop aims to establish a collaborative forum for scholars and researchers to work towards enabling low-resource language research to a higher extent.

The workshop will focus on the emerging fields of NLP (but not limited to):  

• Addressing Data Scarcity Low resource data

• Leveraging Multimodal Data fusion and Integration for Social Media Data Analytics

• AI-driven solutions for linguistic diversity

• Online content moderation in low-resource language on social media

• Computational linguistics Perspectives

• Social Media data in Crisis management

• Performance Evaluation of NLP and Computer Vision tasks in low-resource languages

Publication

 Workshops will be held at the following conference venue:

SPELLL 2023 (Second International Conference on Speech and Language Technologies for Low-Resource Languages) will be held in Tamil Nadu, India from December 06-08, 2023 and the workshops will be held on December 07-08, 2023.

• All Accepted papers that are presented at the conference will be published in the Springer series: Communications in Computer and Information Science (CCIS) - Scopus Indexed 

• Volumes published will be indexed in the Conference Proceedings Citation Index (CPCI) - part of Clarivate Analytics’ Web of Science, EI Engineering Index, ACM Digital Library, DBLP, Google Scholar, and Scopus.