Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
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 | Venue PDF | 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. |