no code implementations • NAACL (SUKI) 2022 • Samyadeep Basu, Amr Sharaf, Karine Ip Kiun Chong, Alex Fischer, Vishal Rohra, Michael Amoake, Hazem El-Hammamy, Ehi Nosakhare, Vijay Ramani, Benjamin Han
Intent classification (IC) and slot filling (SF) are two fundamental tasks in modern Natural Language Understanding (NLU) systems.
1 code implementation • 16 Jan 2024 • Haoran Xu, Amr Sharaf, Yunmo Chen, Weiting Tan, Lingfeng Shen, Benjamin Van Durme, Kenton Murray, Young Jin Kim
However, even the top-performing 13B LLM-based translation models, like ALMA, does not match the performance of state-of-the-art conventional encoder-decoder translation models or larger-scale LLMs such as GPT-4.
1 code implementation • 20 Sep 2023 • Haoran Xu, Young Jin Kim, Amr Sharaf, Hany Hassan Awadalla
In this study, we propose a novel fine-tuning approach for LLMs that is specifically designed for the translation task, eliminating the need for the abundant parallel data that traditional translation models usually depend on.
no code implementations • 24 May 2023 • Vikas Raunak, Amr Sharaf, Yiren Wang, Hany Hassan Awadallah, Arul Menezes
In this work, we formalize the task of direct translation post-editing with Large Language Models (LLMs) and explore the use of GPT-4 to automatically post-edit NMT outputs across several language pairs.
1 code implementation • 18 Feb 2023 • Amr Hendy, Mohamed Abdelrehim, Amr Sharaf, Vikas Raunak, Mohamed Gabr, Hitokazu Matsushita, Young Jin Kim, Mohamed Afify, Hany Hassan Awadalla
In this paper, we present a comprehensive evaluation of GPT models for machine translation, covering various aspects such as quality of different GPT models in comparison with state-of-the-art research and commercial systems, effect of prompting strategies, robustness towards domain shifts and document-level translation.
no code implementations • 21 Oct 2021 • Samyadeep Basu, Amr Sharaf, Nicolo Fusi, Soheil Feizi
To address the issue of sub-par performance on hard episodes, we investigate and benchmark different meta-training strategies based on adversarial training and curriculum learning.
no code implementations • 29 Sep 2021 • Liam H Fowl, Micah Goldblum, Arjun Gupta, Amr Sharaf, Tom Goldstein
We validate and deploy this metric on both images and text.
no code implementations • 17 Sep 2021 • Samyadeep Basu, Karine lp Kiun Chong, Amr Sharaf, Alex Fischer, Vishal Rohra, Michael Amoake, Hazem El-Hammamy, Ehi Nosakhare, Vijay Ramani, Benjamin Han
Intent classification (IC) and slot filling (SF) are two fundamental tasks in modern Natural Language Understanding (NLU) systems.
1 code implementation • 14 Oct 2020 • Renkun Ni, Micah Goldblum, Amr Sharaf, Kezhi Kong, Tom Goldstein
Conventional image classifiers are trained by randomly sampling mini-batches of images.
no code implementations • 13 Oct 2020 • Liam Fowl, Micah Goldblum, Arjun Gupta, Amr Sharaf, Tom Goldstein
We validate and deploy this metric on both images and text.
1 code implementation • ACL 2020 • Kianté Brantley, Amr Sharaf, Hal Daumé III
Imitation learning algorithms provide state-of-the-art results on many structured prediction tasks by learning near-optimal search policies.
no code implementations • WS 2020 • Amr Sharaf, Hany Hassan, Hal Daumé III
We frame the adaptation of NMT systems as a meta-learning problem, where we learn to adapt to new unseen domains based on simulated offline meta-training domain adaptation tasks.
no code implementations • 25 Sep 2019 • Amr Sharaf, Hal Daumé III
We develop a meta-learning algorithm, MELEE, that learns an exploration policy based on simulated, synthetic contextual bandit tasks.
no code implementations • ICLR 2019 • Amr Sharaf, Hal Daumé III
We describe MELEE, a meta-learning algorithm for learning a good exploration policy in the interactive contextual bandit setting.
no code implementations • 27 Nov 2018 • Amr Sharaf, Arpit Gupta, Hancheng Ge, Chetan Naik, Lambert Mathias
In the cross-lingual setup, we assume there is access to annotated resources as well as a well trained model in the source language and little to no annotated data in the target language.
1 code implementation • ICLR 2018 • Hal Daumé III, John Langford, Amr Sharaf
We consider reinforcement learning and bandit structured prediction problems with very sparse loss feedback: only at the end of an episode.
no code implementations • WS 2017 • Amr Sharaf, Hal Daum{\'e} III
We present an algorithm for structured prediction under online bandit feedback.
no code implementations • WS 2017 • Amr Sharaf, Shi Feng, Khanh Nguyen, Kianté Brantley, Hal Daumé III
We describe the University of Maryland machine translation systems submitted to the WMT17 German-English Bandit Learning Task.