Super-naturalinstructions: Generalization via declarative instructions on 1600+ nlp tasks Y Wang, S Mishra, P Alipoormolabashi, Y Kordi, A Mirzaei, A Arunkumar, ... EMNLP 2022, 2022 | 530* | 2022 |
In-boxbart: Get instructions into biomedical multi-task learning M Parmar, S Mishra, M Purohit, M Luo, MH Murad, C Baral NAACL 2022 Findings, 2022 | 50 | 2022 |
Don't Blame the Annotator: Bias Already Starts in the Annotation Instructions M Parmar, S Mishra, M Geva, C Baral EACL 2023 (Outstanding Paper Award), 2023 | 48 | 2023 |
Residual neural network precisely quantifies dysarthria severity-level based on short-duration speech segments S Gupta, AT Patil, M Purohit, M Parmar, M Patel, HA Patil, RC Guido Neural Networks 139, 105-117, 2021 | 40 | 2021 |
Is a Question Decomposition Unit All We Need? P Patel, S Mishra, M Parmar, C Baral EMNLP 2022, 2022 | 32 | 2022 |
Effectiveness of cross-domain architectures for whisper-to-normal speech conversion M Parmar, S Doshi, NJ Shah, M Patel, HA Patil 2019 27th European Signal Processing Conference (EUSIPCO), 1-5, 2019 | 22 | 2019 |
Less is more: Summary of long instructions is better for program synthesis K Kuznia, S Mishra, M Parmar, C Baral EMNLP 2022, 2022 | 19 | 2022 |
Novel Adaptive Generative Adversarial Network for Voice Conversion M Patel, M Parmar, S Doshi, N Shah, HA Patil Asia-Pacific Signal and Information Processing Association (APSIPA), 1273-1281, 2019 | 17* | 2019 |
Novel MMSE DiscoGAN for cross-domain whisper-to-speech conversion NJ Shah, M Parmar, N Shah, HA Patil Machine Learning in Speech and Language Processing (MLSLP) Workshop, 1-3, 2018 | 17 | 2018 |
How Many Data Samples is an Additional Instruction Worth? RS Puri, S Mishra, M Parmar, C Baral EACL 2023 Findings, 2023 | 16 | 2023 |
Biotabqa: Instruction learning for biomedical table question answering M Luo, S Saxena, S Mishra, M Parmar, C Baral arXiv preprint arXiv:2207.02419, 2022 | 14 | 2022 |
Novel Inception-GAN for Whisper-to-Normal speech conversion M Patel, M Parmar, S Doshi, N Shah, HA Patil Proceedings of 10th ISCA Speech Synthesis Workshop (SSW 10), Vienna, Austria …, 2019 | 12 | 2019 |
Intelligibility improvement of dysarthric speech using mmse discogan M Purohit, M Patel, H Malaviya, A Patil, M Parmar, N Shah, S Doshi, ... 2020 International Conference on Signal Processing and Communications (SPCOM …, 2020 | 11 | 2020 |
Targen: Targeted data generation with large language models H Gupta, K Scaria, U Anantheswaran, S Verma, M Parmar, SA Sawant, ... arXiv preprint arXiv:2310.17876, 2023 | 10 | 2023 |
Weak speech supervision: A case study of dysarthria severity classification M Purohit, M Parmar, M Patel, H Malaviya, HA Patii 2020 28th European Signal Processing Conference (EUSIPCO), 101-105, 2021 | 5 | 2021 |
Towards logiglue: A brief survey and a benchmark for analyzing logical reasoning capabilities of language models M Luo, S Kumbhar, M Parmar, N Varshney, P Banerjee, S Aditya, C Baral arXiv preprint arXiv:2310.00836, 2023 | 4 | 2023 |
Accelerating llama inference by enabling intermediate layer decoding via instruction tuning with lite N Varshney, A Chatterjee, M Parmar, C Baral arXiv e-prints, arXiv: 2310.18581, 2023 | 4 | 2023 |
Edm3: Event detection as multi-task text generation U Anantheswaran, H Gupta, M Parmar, KK Pal, C Baral arXiv preprint arXiv:2305.16357, 2023 | 4 | 2023 |
Longbox: Evaluating transformers on long-sequence clinical tasks M Parmar, A Naik, H Gupta, D Agrawal, C Baral arXiv preprint arXiv:2311.09564, 2023 | 3 | 2023 |
Can NLP Models Correctly Reason Over Contexts that Break the Common Assumptions? N Varshney, M Parmar, N Patel, D Handa, S Sarkar, M Luo, C Baral arXiv preprint arXiv:2305.12096, 2023 | 3 | 2023 |