no code implementations • EMNLP (sdp) 2020 • Rohan Bhambhoria, Luna Feng, Dawn Sepehr, John Chen, Conner Cowling, Sedef Kocak, Elham Dolatabadi
Automatically generating question answer (QA) pairs from the rapidly growing coronavirus-related literature is of great value to the medical community.
no code implementations • 18 Apr 2024 • Rohan Bhambhoria, Samuel Dahan, Jonathan Li, Xiaodan Zhu
This study evaluates the performance of general-purpose AI, like ChatGPT, in legal question-answering tasks, highlighting significant risks to legal professionals and clients.
no code implementations • 25 May 2023 • Chu Fei Luo, Rohan Bhambhoria, Samuel Dahan, Xiaodan Zhu
Deep learning has made significant progress in the past decade, and demonstrates potential to solve problems with extensive social impact.
no code implementations • 24 May 2023 • Rohan Bhambhoria, Lei Chen, Xiaodan Zhu
To address these limitations, we propose the use of entailment-contradiction prediction in conjunction with LLMs, which allows for strong performance in a strict zero-shot setting.
1 code implementation • 23 May 2023 • Chu Fei Luo, Rohan Bhambhoria, Xiaodan Zhu, Samuel Dahan
With this task definition, automatic hate speech detection can be more closely aligned to enforceable laws, and hence assist in more rigorous enforcement of legal protections against harmful speech in public forums.
1 code implementation • 20 May 2023 • Jonathan Li, Will Aitken, Rohan Bhambhoria, Xiaodan Zhu
Parameter-efficient tuning aims to mitigate the large memory requirements of adapting pretrained language models for downstream tasks.
no code implementations • 25 Oct 2022 • Jonathan Li, Rohan Bhambhoria, Xiaodan Zhu
Unfortunately, parameter-efficient methods perform poorly with small amounts of data, which are common in the legal domain (where data labelling costs are high).
no code implementations • 1 Jan 2022 • Rohan Bhambhoria, Hui Liu, Samuel Dahan, Xiaodan Zhu
In this work, we utilize deep learning models in the area of trademark law to shed light on the issue of likelihood of confusion between trademarks.