Are Noisy Sentences Useless for Distant Supervised Relation Extraction?
Authors: Yuming Shang, He-Yan Huang, Xian-Ling Mao, Xin Sun, Wei Wei8799-8806
AAAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experimental results demonstrate that our model outperforms the state-of-the-art baselines on a popular benchmark dataset, and can indeed alleviate the noisy labeling problem. |
| Researcher Affiliation | Collaboration | 1School of Computer Science, Beijing Institute of Technology, Beijing, China 2CETC Big Data Research Institute Co., Ltd., Guiyang, China,550022 3Huazhong University of Science and Technology, Hu bei, China 4Big Data Application on lmproving Government Governance Capabilities National Engineering Laboratory Guiyang, China, 550022 |
| Pseudocode | No | The paper describes the model architecture and procedures textually and with a diagram (Figure 1), but it does not include any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper provides links to the codebases for several baseline models that were used for comparison. However, it does not explicitly state that the code for their proposed model (DCRE) is open-source or provide a link to its repository. |
| Open Datasets | Yes | We evaluate the proposed method on a widely used dataset NYT-10 (Riedel, Yao, and Mccallum 2010) which was constructed by aligning relation facts in Freebase (Bollacker et al. 2008) with the New York Times (NYT) corpus. |
| Dataset Splits | No | The paper explicitly states the use of 'training data' and 'test data' with specific sizes and timeframes. However, it does not explicitly mention or specify a separate 'validation' dataset or split used for hyperparameter tuning or model selection. |
| Hardware Specification | No | The paper describes the experimental setup, but it does not provide any specific details about the hardware used (e.g., CPU/GPU models, memory specifications) for running the experiments. |
| Software Dependencies | No | The paper mentions using PCNN as a feature extractor, but it does not list any specific software dependencies with their version numbers (e.g., programming languages, libraries, frameworks, or solvers with version numbers). |
| Experiment Setup | Yes | Table 2: Parameters Setting lists specific values for various hyperparameters and settings: Kernel size 3, Feature maps 230, Word embedding dimension 50, Position embedding dimension 5, Pre-train learning rate 0.4, Clustering learning rate 0.004, Model learning rate 0.1, Threshold φ 0.1, Dropout 0.5, Coefficient λ 0.6. |