A Relation-Specific Attention Network for Joint Entity and Relation Extraction
Authors: Yue Yuan, Xiaofei Zhou, Shirui Pan, Qiannan Zhu, Zeliang Song, Li Guo
IJCAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experiments on two public datasets show that our model can effectively extract overlapping triplets and achieve state-of-the-art performance. Our code is available at https://github.com/Anery/RSAN |
| Researcher Affiliation | Academia | Yue Yuan1,2 , Xiaofei Zhou1,2 , Shirui Pan3 , Qiannan Zhu1,2 , Zeliang Song1,2 and Li Guo1,2 1Institute of Information Engineering, Chinese Academy of Sciences 2University of Chinese Academy of Sciences, School of Cyber Security 3Faculty of Information Technology, Monash University |
| Pseudocode | No | The paper describes the model and its components in detail but does not provide any explicitly labeled pseudocode or algorithm blocks. |
| Open Source Code | Yes | Our code is available at https://github.com/Anery/RSAN |
| Open Datasets | Yes | Following [Zeng et al., 2018], we evaluate our model on two widely used datasets: New York Times (NYT) and Web NLG. |
| Dataset Splits | Yes | Data Set NYT Web NLG Relation types 24 246 Tain sentences 56195 5019 Dev sentences 5000 500 Test sentences 5000 703 |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., GPU/CPU models, memory) used for running the experiments. |
| Software Dependencies | No | The paper mentions training with |
| Experiment Setup | Yes | We set the dimension of word embedding dw = 100, POS embedding dpos = 15, character embedding dc = 50, and relation embedding dr = 300. ... Hidden State of the encoder Bi LSTM (dhe), attention (datt), gate (dg) and the decoder Bi LSTM (dhd) are all set to 300 dimensions. The sentence-level relational negative sampled number nneg is set to 4. The model is trained using Adam [Kingma and Ba, 2014] with learning rate of 0.001 and batch size of 16. We apply dropout mechanism to the embedding layer with a rate of 0.5 to avoid overfitting. |