Mihir Kale

Publications by Year

Research Areas

Topic Modeling, Natural Language Processing Techniques, Multimodal Machine Learning Applications, Speech Recognition and Synthesis, Speech and dialogue systems

Most-Cited Works

• → mT5: A Massively Multilingual Pre-trained Text-to-Text Transformer(2021)1,512 cited
• → ByT5: Towards a Token-Free Future with Pre-trained Byte-to-Byte Models(2022)222 cited
• → Gemma: Open Models Based on Gemini Research and Technology(2024)220 cited
• → The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics(2021)148 cited
• → Text-to-Text Pre-Training for Data-to-Text Tasks(2020)138 cited
• → Template Guided Text Generation for Task-Oriented Dialogue(2020)56 cited