Leveraging Document-Level Label Consistency for Named Entity Recognition
Authors: Tao Gui, Jiacheng Ye, Qi Zhang, Yaqian Zhou, Yeyun Gong, Xuanjing Huang
IJCAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | The experimental results on three named entity recognition benchmarks demonstrated that the proposed method significantly outperformed the state-of-the-art methods. |
| Researcher Affiliation | Collaboration | 1School of Computer Science, Fudan University, Shanghai, China 2Microsoft Research Asia |
| Pseudocode | No | The paper describes its model architecture and training procedures through text, equations, and diagrams, but it does not include any explicit pseudocode blocks or algorithms. |
| Open Source Code | Yes | Our codes are released at Github1. |
| Open Datasets | Yes | We conduct experiments on three benchmark NER datasets. We follow the standard split of each corpora. Statistics are listed in Table 1. Co NLL2003. The shared task of the Co NLL2003 dataset [Tjong Kim Sang and De Meulder, 2003]... Onto Notes 5.0. The English NER dataset Onto Notes 5.0 [Weischedel et al., 2013]... CHEMDNER. The CHEMDNER corpus... [Krallinger et al., 2015] |
| Dataset Splits | Yes | We follow the standard split of each corpora. Statistics are listed in Table 1. |
| Hardware Specification | Yes | The computations for a single model are run on a Ge Force GTX 1080Ti GPU. |
| Software Dependencies | No | The paper mentions using specific embeddings (Glove, word2vec, BERT, ELMo) and a framework (fast NLP), but it does not provide specific version numbers for core software dependencies like Python or deep learning libraries (e.g., PyTorch, TensorFlow). |
| Experiment Setup | Yes | Following [Ma and Hovy, 2016; Qian et al., 2019; Luo et al., 2020], we use the same 100-dimensional Glove embedding2 [Pennington et al., 2014] as word embedding for the Co NLL2003 and Onto Notes datasets. For CHEMDNER, we use 50-dimensional pretrained word2vec [Mikolov et al., 2013] embedding, which is the same as [Qian et al., 2019]. For Char CNN, we use 32-dimensional character embeddings and 32 filters of width 3 for Co NLL2003 and Onto Notes, and 128-dimensional character embeddings and 128 filters of width 2 to 4 for CHEMDNER. For the first stage, we use 1 layer of VLSTM with 200 dimensions for Co NLL2003 and 2 layers for the other datasets. For the second stage, we use 3 layers and 4 layers of Transformer for Co NLL2003, Onto Notes and CHEMDNER, respectively. Dropout is set to 0.5, and the number of samples is set to 32 for all the datasets. The standard entity-level F1 score is used as evaluation metric. For all the experiments, we use the BIOES tag scheme instead of standard BIO2, as previous studies have reported a meaningful improvement with this scheme [Ma and Hovy, 2016; Lample et al., 2016]. |