no code implementations • 22 Oct 2022 • Bashar Alhafni, Nizar Habash, Houda Bouamor, Ossama Obeid, Sultan Alrowili, Daliyah AlZeer, Khawlah M. Alshanqiti, Ahmed ElBakry, Muhammad ElNokrashy, Mohamed Gabr, Abderrahmane Issam, Abdelrahim Qaddoumi, K. Vijay-Shanker, Mahmoud Zyate
In this paper, we present the results and findings of the Shared Task on Gender Rewriting, which was organized as part of the Seventh Arabic Natural Language Processing Workshop.
no code implementations • 18 Jan 2022 • Mehmet Efruz Karabulut, K. Vijay-Shanker
In this project, we study a state-of-the-art deep learning model, which we called SSN-4 model here.
1 code implementation • 11 Nov 2021 • Mehmet Efruz Karabulut, K. Vijay-Shanker, Yifan Peng
Our system obtained 0. 7708 in precision and 0. 7770 in recall, for an F1 score of 0. 7739, demonstrating the effectiveness of using ensembles of BERT-based language models for automatically detecting relations between chemicals and proteins.
1 code implementation • NAACL (BioNLP) 2021 • Peng Su, Yifan Peng, K. Vijay-Shanker
In this work, we explore the method of employing contrastive learning to improve the text representation from the BERT model for relation extraction.
no code implementations • 1 Nov 2020 • Peng Su, K. Vijay-Shanker
In this paper, we will investigate the method of utilizing the entire layer in the fine-tuning process of BERT model.
no code implementations • 8 May 2020 • Peng Su, K. Vijay-Shanker
Adversarial training is a technique of improving model performance by involving adversarial examples in the training process.
no code implementations • WS 2017 • Gang Li, Cathy Wu, K. Vijay-Shanker
Distant supervision has been applied to automatically generate labeled data for biomedical relation extraction.
no code implementations • WS 2017 • Samir Gupta, A.S.M. Ashique Mahmood, Karen Ross, Cathy Wu, K. Vijay-Shanker
Comparison sentences are very commonly used by authors in biomedical literature to report results of experiments.
no code implementations • 31 Oct 2014 • John E. Miller, Michael Bloodgood, Manabu Torii, K. Vijay-Shanker
Part-of-speech (POS) tagging is a fundamental component for performing natural language tasks such as parsing, information extraction, and question answering.
no code implementations • 17 Sep 2014 • Michael Bloodgood, K. Vijay-Shanker
Actively sampled data can have very different characteristics than passively sampled data.
no code implementations • 17 Sep 2014 • Michael Bloodgood, K. Vijay-Shanker
A survey of existing methods for stopping active learning (AL) reveals the needs for methods that are: more widely applicable; more aggressive in saving annotations; and more stable across changing datasets.
no code implementations • 12 Sep 2014 • Michael Bloodgood, K. Vijay-Shanker
There is a broad range of BioNLP tasks for which active learning (AL) can significantly reduce annotation costs and a specific AL algorithm we have developed is particularly effective in reducing annotation costs for these tasks.