Picture for Shahram Khadivi

Shahram Khadivi

IKUN for WMT24 General MT Task: LLMs Are here for Multilingual Machine Translation

Add code
Aug 21, 2024
Figure 1 for IKUN for WMT24 General MT Task: LLMs Are here for Multilingual Machine Translation
Figure 2 for IKUN for WMT24 General MT Task: LLMs Are here for Multilingual Machine Translation
Figure 3 for IKUN for WMT24 General MT Task: LLMs Are here for Multilingual Machine Translation
Figure 4 for IKUN for WMT24 General MT Task: LLMs Are here for Multilingual Machine Translation
Viaarxiv icon

LiLiuM: eBay's Large Language Models for e-commerce

Add code
Jun 17, 2024
Viaarxiv icon

ITEm: Unsupervised Image-Text Embedding Learning for eCommerce

Add code
Oct 22, 2023
Viaarxiv icon

Document-Level Language Models for Machine Translation

Add code
Oct 18, 2023
Viaarxiv icon

Active Continual Learning: Labelling Queries in a Sequence of Tasks

Add code
May 06, 2023
Viaarxiv icon

Multi-armed bandits for online optimization of language model pre-training: the use case of dynamic masking

Add code
Mar 24, 2022
Figure 1 for Multi-armed bandits for online optimization of language model pre-training: the use case of dynamic masking
Figure 2 for Multi-armed bandits for online optimization of language model pre-training: the use case of dynamic masking
Figure 3 for Multi-armed bandits for online optimization of language model pre-training: the use case of dynamic masking
Figure 4 for Multi-armed bandits for online optimization of language model pre-training: the use case of dynamic masking
Viaarxiv icon

A Preordered RNN Layer Boosts Neural Machine Translation in Low Resource Settings

Add code
Dec 28, 2021
Figure 1 for A Preordered RNN Layer Boosts Neural Machine Translation in Low Resource Settings
Figure 2 for A Preordered RNN Layer Boosts Neural Machine Translation in Low Resource Settings
Figure 3 for A Preordered RNN Layer Boosts Neural Machine Translation in Low Resource Settings
Viaarxiv icon

Towards Reinforcement Learning for Pivot-based Neural Machine Translation with Non-autoregressive Transformer

Add code
Sep 27, 2021
Figure 1 for Towards Reinforcement Learning for Pivot-based Neural Machine Translation with Non-autoregressive Transformer
Figure 2 for Towards Reinforcement Learning for Pivot-based Neural Machine Translation with Non-autoregressive Transformer
Figure 3 for Towards Reinforcement Learning for Pivot-based Neural Machine Translation with Non-autoregressive Transformer
Figure 4 for Towards Reinforcement Learning for Pivot-based Neural Machine Translation with Non-autoregressive Transformer
Viaarxiv icon

Integrated Training for Sequence-to-Sequence Models Using Non-Autoregressive Transformer

Add code
Sep 27, 2021
Figure 1 for Integrated Training for Sequence-to-Sequence Models Using Non-Autoregressive Transformer
Figure 2 for Integrated Training for Sequence-to-Sequence Models Using Non-Autoregressive Transformer
Figure 3 for Integrated Training for Sequence-to-Sequence Models Using Non-Autoregressive Transformer
Figure 4 for Integrated Training for Sequence-to-Sequence Models Using Non-Autoregressive Transformer
Viaarxiv icon

Back-translation for Large-Scale Multilingual Machine Translation

Add code
Sep 17, 2021
Figure 1 for Back-translation for Large-Scale Multilingual Machine Translation
Figure 2 for Back-translation for Large-Scale Multilingual Machine Translation
Figure 3 for Back-translation for Large-Scale Multilingual Machine Translation
Figure 4 for Back-translation for Large-Scale Multilingual Machine Translation
Viaarxiv icon