Unified Named Entity Recognition as Word-Word Relation Classification
Authors: Jingye Li, Hao Fei, Jiang Liu, Shengqiong Wu, Meishan Zhang, Chong Teng, Donghong Ji, Fei Li10965-10973
AAAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We perform extensive experiments on 14 widely-used benchmark datasets for flat, overlapped, and discontinuous NER (8 English and 6 Chinese datasets), where our model beats all the current top-performing baselines, pushing the state-of-the-art performances of unified NER. |
| Researcher Affiliation | Academia | 1 Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, China 2 Institute of Computing and Intelligence, Harbin Institute of Technology (Shenzhen), China |
| Pseudocode | No | The paper describes its architecture and formulations but does not include any pseudocode or algorithm blocks. |
| Open Source Code | Yes | Our code is available at https://github. com/ljynlp/W2NER. |
| Open Datasets | Yes | To evaluate our framework for three NER subtasks, we conducted experiments on 14 datasets. Flat NER Datasets We adopt Co NLL-2003 (Sang and Meulder 2003) and Onto Notes 5.0 (Pradhan et al. 2013b) in English, Onto Notes 4.0 (Weischedel et al. 2011), MSRA (Levow 2006), Weibo (Peng and Dredze 2015; He and Sun 2017), and Resume (Zhang and Yang 2018) in Chinese. [...] Overlapped NER Datasets We conduct experiments on ACE 2004 (Doddington et al. 2004), ACE 2005 (Walker et al. 2011), GENIA (Kim et al. 2003). [...] Discontinuous NER Datasets We experiment on three datasets for discontinuous NER, namely CADEC (Karimi et al. 2015), Sh ARe13 (Pradhan et al. 2013a) and Sh ARe14 (Mowery et al. 2014). |
| Dataset Splits | Yes | For GENIA, we follow Yan et al. (2021) to use five types of entities and split the train/dev/test as 8.1:0.9:1.0. For ACE 2004 and ACE 2005 in English, we use the same data split as Lu and Roth (2015); Yu et al. (2020). For ACE 2004 and ACE 2005 in Chinese, we split the train/dev/test as 8.0:1.0:1.0. We use the preprocessing scripts provided by Dai et al. (2020) for data splitting. |
| Hardware Specification | No | The paper mentions using BERT and Bi-LSTM but does not specify any hardware details such as GPU models, CPU types, or other computing resources used for the experiments. |
| Software Dependencies | No | The paper mentions using BERT and Bi-LSTM, but it does not specify any software versions for libraries, frameworks, or programming languages (e.g., PyTorch version, Python version, CUDA version). |
| Experiment Setup | No | The paper states: "We employ the same experimental settings in previous work (Lample et al. 2016; Yan et al. 2021; Ma et al. 2020; Li et al. 2020b)." However, it does not explicitly provide specific hyperparameter values (e.g., learning rate, batch size, number of epochs) or detailed training configurations within the main text. |