Global Structure and Local Semantics-Preserved Embeddings for Entity Alignment
Authors: Hao Nie, Xianpei Han, Le Sun, Chi Man Wong, Qiang Chen, Suhui Wu, Wei Zhang
IJCAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experiments on several real-world datasets show that our method significantly outperforms other entity alignment approaches and achieves the new state-of-the-art performance. |
| Researcher Affiliation | Collaboration | Hao Nie1,3 , Xianpei Han1,2 , Le Sun1,2 , Chi Man Wong4 , Qiang Chen4 , Suhui Wu4 and Wei Zhang4 1Chinese Information Processing Laboratory, Institute of Software, Chinese Academy of Sciences 2State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences 3University of Chinese Academy of Sciences 4Alibaba Group {niehao2016, xianpei, sunle}@iscas.ac.cn, {chiman.wcm, lapu.cq, linnai.wsh, lantu.zw}@alibaba-inc.com |
| Pseudocode | No | The paper describes the model architecture and mathematical equations but does not include any pseudocode or clearly labeled algorithm blocks. |
| Open Source Code | No | The paper does not contain any explicit statement about releasing source code for the described methodology or a link to a code repository. |
| Open Datasets | Yes | Datasets. We evaluate different methods using the following benchmark datasets. DBP15K [Sun et al., 2017] is extracted from DBpedia... DWY100K [Sun et al., 2018] contains two large-scale monolingual datasets, namely DBP-WD (DBpedia Wikidata) and DBP-YG (DBpedia-YAGO3). |
| Dataset Splits | Yes | All the datasets use the 3:7 train-test split. The hyper-parameters used in our model are tuned on development set and their values are: β1 = 0.2, β2 = 2.0, α = 0.8. |
| Hardware Specification | No | The paper mentions 'computing resources' but does not provide specific hardware details such as GPU/CPU models, memory, or detailed computer specifications used for experiments. |
| Software Dependencies | No | The paper states 'We implement our model using Pytorch a popular deep learning framework' but does not specify the version number of PyTorch or any other software dependencies. |
| Experiment Setup | Yes | The hyper-parameters used in our model are tuned on development set and their values are: β1 = 0.2, β2 = 2.0, α = 0.8. The dimensionality for embeddings in DBP15K and DWY100K datasets are 300 and 200 respectively. We set different learning rates for the structure preserving network and semantics-based refining network, they are 0.001 and 0.005 respectively. For DBP15K dataset, we uniformly sample 20 negative examples in its nearest neighbors for each relational triple (half for head and tail entities respectively), for DWY100K, the sampling size is 30. |