I’m thrilled to announce that our paper on AI Safety for Geospatial AI has been accepted to ACL Findings! 🎉 Yesterday, I had the privilege of presenting our work virtually at the AACL-IJCNLP 2025 conference in Mumbai. As LLMs become increasingly integrated into critical applications, AI safety has never been more important — especially when handling sensitive geospatial data and mitigating the associated risks. ...
In this article we will be discussing the research paper on text classficiation using label names. The research paper is titled: Text Classification Using Label Names Only: A Language Model Self-Training Approach and it is published in the Conference on Empirical Methods in Natural Language Processing 2020. The research paper is available here So far, text classification has seen a huge succes in the NLP domain with the help of huge chunks of labelled data that is fed on to the models for training purposes. Recently, Semi Supervised learning has boomed using abundant unlabelled data and a smaller amount of labelled data. But when the number of classes are huge, it becomes a tedious task for the domain experts. ...
In this article we will be discussing the research paper on grammar error correction in morphologically rich languages especially in Russian Languages. The research paper is titled: The Grammar Error Correction in Morphologically Rich Languages: The Case of Russian and it is published in the Journal of Language Technology. The research paper is available here Rozovskaya and Roth 2019, uses a corpus of the Russian Learner Corpus of Academic Writing (RULEC, 560K words) which is written by students in United States learning Russian. ...