1 code implementation • COLING 2022 • Amit Pandey, Avani Gupta, Vikram Pudi
The paper aims to identify cited text spans in the reference paper related to the given citance in the citing paper.
no code implementations • ICON 2021 • Swayatta Daw, Shivprasad Sagare, Tushar Abhishek, Vikram Pudi, Vasudeva Varma
We propose cross-lingual pairing of English triples with Hindi sentences to mitigate the unavailability of content overlap.
1 code implementation • 28 Dec 2022 • Suba S, Nita Parekh, Ramesh Loganathan, Vikram Pudi, Chinnababu Sunkavalli
One of the major concerns in using ma-chine learning (ML) approaches for automatic processing of CT scan images in clinical setting is that these methods are trained on limited and biased sub-sets of publicly available COVID-19 data.
1 code implementation • SemEval (NAACL) 2022 • Amit Pandey, Swayatta Daw, Narendra Babu Unnam, Vikram Pudi
We leverage pre-trained language models to solve the task of complex NER for two low-resource languages: Chinese and Spanish.
1 code implementation • NAACL 2022 • Vivek Kumar, Rishabh Maheshwary, Vikram Pudi
Extensive experiments on two benchmark datasets across three state-of-the-art MWP solvers show that proposed methods increase the generalization and robustness of existing solvers.
1 code implementation • SemEval (NAACL) 2022 • Amit Pandey, Swayatta Daw, Vikram Pudi
We qualitatively analyze the performance of multiple architectures for this task.
1 code implementation • Findings (EMNLP) 2021 • Vivek Kumar, Rishabh Maheshwary, Vikram Pudi
Standard accuracy metrics have shown that Math Word Problem (MWP) solvers have achieved high performance on benchmark datasets.
1 code implementation • EMNLP 2021 • Rishabh Maheshwary, Saket Maheshwary, Vikram Pudi
Also, prior attacks do not maintain a consistent search space while comparing different search methods.
3 code implementations • 29 Dec 2020 • Rishabh Maheshwary, Saket Maheshwary, Vikram Pudi
Our proposed attack strategy leverages population-based optimization algorithm to craft plausible and semantically similar adversarial examples by observing only the top label predicted by the target model.
1 code implementation • 24 Dec 2020 • Rishabh Maheshwary, Saket Maheshwary, Vikram Pudi
We study an important task of attacking natural language processing models in a black box setting.
no code implementations • WS 2019 • Kritika Agrawal, Aakash Mittal, Vikram Pudi
In this paper, we propose a novel, scalable, semi-supervised method for extracting relevant structured information from the vast available raw scientific literature.
1 code implementation • 25 Nov 2018 • Noveen Sachdeva, Giuseppe Manco, Ettore Ritacco, Vikram Pudi
We introduce a recurrent version of the VAE, where instead of passing a subset of the whole history regardless of temporal dependencies, we rather pass the consumption sequence subset through a recurrent neural network.
Ranked #2 on Recommendation Systems on MovieLens 1M (nDCG@100 metric)
1 code implementation • IEEE IEEE International Conference on Data Mining (ICDM) 2017 • Ambika Kaul, Saket Maheshwary, Vikram Pudi
In recent years, the importance of feature engineering has been confirmed by the exceptional performance of deep learning techniques, that automate this task for some applications.
no code implementations • IJCNLP 2017 • P, Prakhar ey, Vikram Pudi, Manish Shrivastava
Word embeddings learned from text corpus can be improved by injecting knowledge from external resources, while at the same time also specializing them for similarity or relatedness.