Search Results for author:
Found 5 papers, 1 papers with code
Context or No Context? A preliminary exploration of human-in-the-loop approach for Incremental Temporal Summarization in meetings
By compressing the previous contexts by ~70%, we achieve better ROUGE scores over our baseline models.
Selecting Informative Contexts Improves Language Model Fine-tuning
Here we present a general fine-tuning method that we call information gain filtration for improving the overall training efficiency and final performance of language model fine-tuning.
Slower is Better: Revisiting the Forgetting Mechanism in LSTM for Slower Information Decay
Altogether, we found that LSTM with the proposed forget gate can learn long-term dependencies, outperforming other recurrent networks in multiple domains; such gating mechanism can be integrated into other architectures for improving the learning of long timescale information in recurrent neural networks.
Imitation Learning for Neural Network Autopilot in Fixed-Wing Unmanned Aerial Systems
The ANN autopilot aims to mimic a unified guidance, navigation & control (GNC) system to fly a fixed-wing UAS.
Selecting Informative Contexts Improves Language Model Finetuning
Here we present a general fine-tuning method that we call information gain filtration for improving the overall training efficiency and final performance of language model fine-tuning.
