Cogint Lab @ASU - build automated systems and develop underlying methodologies and address associated challenges that can understand text, images, and videos.
Congratulate ASU #NLProc students and collaborators on their 8 accepted papers at #EMNLP2022. Our papers cross topics in NLP and V&L: program synthesis, question decomposition, natural instruction, mathematical reasoning, video QA, model efficiency, action reasoning, UI language.
Let the Model Decide its Curriculum for Multitask Learning. Neeraj Varshney, Swaroop Mishra, Chitta Baral. Paper Link: https://t.co/zybXyxGeiW Poster: July 14th 14:15–15:15 PM PDT Regency Ballroom (5/6)
Congrats Cogint-ASU (https://t.co/n9huVMlqXj) members have the following papers accepted to #NAACL2022. Welcome to stop by the presentation or poster session in #NAACL2022 Seattle. Looking forward to your attendance! @Swarooprm7@Mihir3009@man_luo_asu@nrj_varshney (1/6)
In-BoXBART: Get Instructions into Biomedical Multi-Task Learning. Mihir Parmar, Swaroop Mishra, Mirali Purohit, Man Luo, M. Hassan Murad, Chitta Baral. Paper link: https://t.co/rTz65yX95s Poster: July 13th 14:15 – 15:45 PDT, Regency A & B (4/6)
Kirby Kuznia, Swaroop Mishra, Mihir Parmar, Chitta Baral. Less is More: Summary of Long Instructions is Better for Program Synthesis. the Spa-NLP Workshop @ ACL 2022. https://t.co/XQaLl5aPjr (14/14)
Ravsehaj Singh Puri, Swaroop Mishra, Mihir Parmar, Chitta Baral. How Many Data Samples is an Additional Instruction Worth? the Spa-NLP Workshop @ ACL 2022. https://t.co/rfDaMHzjHP (13/14)