FIRE 2022 ILSUM Track: Indian Language Summarization

Abstract

This abstract provides a short overview of the first edition of the shared task on Indian Language Summarization (ILSUM) organized at the 14th Forum for Information Retrieval Evaluation (FIRE 2022). A more detailed discussion is available in the track overview paper. The objective of this shared task was to create benchmark data for text summarization in Indian languages. This edition included three languages Hindi, Gujarati, and Indian English which is an officially recognized dialect of English mainly used in the Indian subcontinent. The task saw an enthusiastic response, with registrations from over 50 teams. A total of 12 teams submitted test runs across the three languages out of which 10 teams submitted working notes. Standard ROUGE metrics were used as the evaluation metric.