Leveraging Multi-Token Entities in Document-Level Named Entity Recognition
Authors: Anwen Hu, Zhicheng Dou, Jian-Yun Nie, Ji-Rong Wen7961-7968
AAAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experimental results on the Co NLL-2003 dataset and Onto Notesnbm dataset show that our model outperforms state-of-the-art sentencelevel and document-level NER methods. |
| Researcher Affiliation | Academia | 1Gaoling School of Artificial Intelligence, Renmin University of China 2School of Information, Renmin University of China 3Beijing Key Laboratory of Big Data Management and Analysis Methods 4Key Laboratory of Data Engineering and Knowledge Engineering, MOE 5Department of Computer Science and Operations Research, University of Montreal {anwenhu, dou, jrwen}@ruc.edu.cn, nie@iro.umontreal.ca |
| Pseudocode | No | The paper describes the model architecture and procedures in text and diagrams but does not include any formal pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide any explicit statement or link for the release of its source code. |
| Open Datasets | Yes | We conduct experiments on the Co NLL-2003 and Onto Notesnbm dataset. Co NLL-2003 dataset (Sang and Meulder 2003)... We build Onto Notesnbm dataset by combining newswire (nw), broadcast news (bn) and magazine (mz) parts of Onto Notes 5.0 (Hovy et al. 2006). |
| Dataset Splits | Yes | The statistics of the two datasets are shown in Table 1. (Table 1: Co NLL-2003 Train 946 14,987 20,3621, Dev 216 3,466 51,362, Test 231 3,684 46,435. Ontonotesnbm Train 3,276 54,971 1,249,399, Dev 469 8,187 188,654, Test 284 4,718 105,056) |
| Hardware Specification | No | The paper mentions computation time but does not provide specific hardware details such as GPU or CPU models used for experiments. |
| Software Dependencies | No | The paper mentions the use of 'glove embedding', 'bert-base', and 'flair' models, but does not provide specific version numbers for these or any other software dependencies, programming languages, or libraries. |
| Experiment Setup | No | The paper describes model architecture and loss functions, but it does not provide specific details on hyperparameters such as learning rate, batch size, number of epochs, or optimizer settings, which are crucial for experiment reproducibility. |