Oshin Agarwal
Oshin Agarwal
Verified email at seas.upenn.edu - Homepage
Title
Cited by
Cited by
Year
Interpretability analysis for named entity recognition to understand system predictions and how they can improve
O Agarwal, Y Yang, BC Wallace, A Nenkova
Computational Linguistics 47 (1), 117-140, 2021
72021
Entity-Switched Datasets: An Approach to Auditing the In-Domain Robustness of Named Entity Recognition Models
O Agarwal, Y Yang, BC Wallace, A Nenkova
arXiv preprint arXiv:2004.04123, 2020
52020
Entity Linking via Dual and Cross-Attention Encoders
O Agarwal, DM Bikel
arXiv preprint arXiv:2004.03555, 2020
42020
Evaluation of Named Entity Coreference
O Agarwal, S Subramanian, A Nenkova, D Roth
Proceedings of the Second Workshop on Computational Models of Reference …, 2019
4*2019
Word Embeddings (Also) Encode Human Personality Stereotypes
O Agarwal, F Durupınar, NI Badler, A Nenkova
Proceedings of the Eighth Joint Conference on Lexical and Computational …, 2019
42019
Predicting annotation difficulty to improve task routing and model performance for biomedical information extraction
Y Yang, O Agarwal, C Tar, BC Wallace, A Nenkova
arXiv preprint arXiv:1905.07791, 2019
42019
Knowledge Graph Based Synthetic Corpus Generation for Knowledge-Enhanced Language Model Pre-training
O Agarwal, H Ge, S Shakeri, R Al-Rfou
arXiv preprint arXiv:2010.12688, 2020
3*2020
Machine Translation Aided Bilingual Data-to-Text Generation and Semantic Parsing
O Agarwal, M Kale, H Ge, S Shakeri, R Al-Rfou
Proceedings of the 3rd WebNLG Workshop on Natural Language Generation from …, 2020
32020
Browsing Health: Information Extraction to Support New Interfaces for Accessing Medical Evidence
S Parikh, E Conrad, O Agarwal, I Marshall, BC Wallace, A Nenkova
Proceedings of the Workshop on Extracting Structured Knowledge from …, 2019
12019
From Toxicity in Online Comments to Incivility in American News: Proceed with Caution
A Hede, O Agarwal, L Lu, DC Mutz, A Nenkova
arXiv preprint arXiv:2102.03671, 2021
2021
The system can't perform the operation now. Try again later.
Articles 1–10