no code implementations • 12 Dec 2023 • Renlong Jie, Xiaojun Meng, Xin Jiang, Qun Liu
Different from the centrality-based ranking methods, our extractive scorer can be trained in an end-to-end manner, with no other requirement of positional assumption.
no code implementations • 23 Aug 2023 • Renlong Jie, Xiaojun Meng, Lifeng Shang, Xin Jiang, Qun Liu
Large language models (LLMs) like ChatGPT and GPT-4 have attracted great attention given their surprising performance on a wide range of NLP tasks.
no code implementations • 22 May 2023 • Renlong Jie, Xiaojun Meng, Lifeng Shang, Xin Jiang, Qun Liu
This study proposes a multitask learning architecture for extractive summarization with coherence boosting.
no code implementations • 14 Jun 2021 • Renlong Jie, Junbin Gao
It is extended from the existing study on differentiable neural architecture search, and we made the backbone architecture transformable rather than fixed during the training process.
no code implementations • 17 Aug 2020 • Renlong Jie, Junbin Gao, Andrey Vasnev, Minh-Ngoc Tran
In this study, we investigate learning rate adaption at different levels based on the hyper-gradient descent framework and propose a method that adaptively learns the optimizer parameters by combining multiple levels of learning rates with hierarchical structures.
no code implementations • 26 Jul 2020 • Renlong Jie, Junbin Gao, Andrey Vasnev, Min-ngoc Tran
Based on this, a novel family of flexible activation functions that can replace sigmoid or tanh in LSTM cells are implemented, as well as a new family by combining ReLU and ELUs.
no code implementations • 25 Sep 2019 • Renlong Jie, Junbin Gao, Andrey Vasnev, Minh-Ngoc Tran
Based on this, we develop two novel flexible activation functions that can be implemented in LSTM cells and auto-encoder layers.