no code implementations • NAACL (ACL) 2022 • Anubhav Shrimal, Avi Jain, Kartik Mehta, Promod Yenigalla
We propose posing NER as a multi-question MRC task, where multiple questions (one question per entity) are considered at the same time for a single text.
no code implementations • ACL (ECNLP) 2021 • Ravi Shankar Mishra, Kartik Mehta, Nikhil Rasiwasia
Experiments on a real-world attribute normalization dataset of 50 attributes show that the embeddings trained using our proposed approach obtain 2. 3% improvement over best string matching and 19. 3% improvement over best unsupervised embeddings.
no code implementations • NAACL 2021 • Kartik Mehta, Ioana Oprea, Nikhil Rasiwasia
We propose a multi-task learning architecture to deal with missing labels in the training data, leading to F1 improvement of 9. 2{\%} for numeric attributes over state-of-the-art single-task architecture.
no code implementations • 19 Apr 2021 • Kartik Mehta, Ioana Oprea, Nikhil Rasiwasia
We propose a multi-task learning architecture to deal with missing labels in the training data, leading to F1 improvement of 9. 2% for numeric attributes over single-task architecture.
no code implementations • IJCNLP 2019 • Sawan Kumar, Shweta Garg, Kartik Mehta, Nikhil Rasiwasia
In this paper, we establish the effectiveness of using hard negatives, coupled with a siamese network and a suitable loss function, for the tasks of answer selection and answer triggering.