1 code implementation • 23 May 2023 • Zihao Fu, Meiru Zhang, Zaiqiao Meng, Yannan Shen, David Buckeridge, Nigel Collier
Infectious disease outbreaks continue to pose a significant threat to human health and well-being.
1 code implementation • 22 May 2023 • Zihao Fu, Yixuan Su, Zaiqiao Meng, Nigel Collier
To alleviate the need of human effort, dictionary-based approaches have been proposed to extract named entities simply based on a given dictionary.
no code implementations • 8 Apr 2023 • Zihao Fu, Wai Lam, Qian Yu, Anthony Man-Cho So, Shengding Hu, Zhiyuan Liu, Nigel Collier
Grounded on our analysis, we propose a novel partial attention language model to solve the attention degeneration problem.
no code implementations • 25 Mar 2023 • Meiru Zhang, Yixuan Su, Zaiqiao Meng, Zihao Fu, Nigel Collier
In this study, we consider a more realistic setting of this task, namely the Oracle-Free Event Extraction (OFEE) task, where only the input context is given without any oracle information, including event type, event ontology and trigger word.
no code implementations • 24 Jan 2023 • Zihao Fu, Anthony Man-Cho So, Nigel Collier
The theoretical bounds explain why and how several existing methods can stabilize the fine-tuning procedure.
1 code implementation • 28 Nov 2022 • Zihao Fu, Haoran Yang, Anthony Man-Cho So, Wai Lam, Lidong Bing, Nigel Collier
How to choose the tunable parameters?
no code implementations • 26 Sep 2022 • Zihao Fu, Yijiang River Dong, Lidong Bing, Wai Lam
As the development of the encoder-decoder architecture, researchers are able to study the text generation tasks with broader types of data.
1 code implementation • 29 Dec 2020 • Zihao Fu, Wai Lam, Anthony Man-Cho So, Bei Shi
The experimental results show that our theoretical framework is applicable in general generation models and our proposed rebalanced encoding approach alleviates the repetition problem significantly.
no code implementations • Asian Chapter of the Association for Computational Linguistics 2020 • Zihao Fu, Bei Shi, Lidong Bing, Wai Lam
In our architecture, we reconstruct KB triples or texts via a closed-loop framework via linking a generator and an extractor.
no code implementations • COLING 2020 • Zihao Fu, Lidong Bing, Wai Lam, Shoaib Jameel
Recently, many KB-to-text generation tasks have been proposed to bridge the gap between knowledge bases and natural language by directly converting a group of knowledge base triples into human-readable sentences.
1 code implementation • EMNLP 2020 • Zihao Fu, Bei Shi, Wai Lam, Lidong Bing, Zhiyuan Liu
This kind of data is much easier to obtain since it can be produced automatically.
1 code implementation • NAACL 2019 • Zihao Fu, Yankai Lin, Zhiyuan Liu, Wai Lam
We also propose a novel auto-encoder based facet component to estimate some facets of the fact.
no code implementations • ACL 2018 • Bei Shi, Zihao Fu, Lidong Bing, Wai Lam
Given reviews from different domains, some existing methods for word embeddings exploit sentiment information, but they cannot produce domain-sensitive embeddings.