Neural Entity Summarization with Joint Encoding and Weak Supervision
Authors: Junyou Li, Gong Cheng, Qingxia Liu, Wen Zhang, Evgeny Kharlamov, Kalpa Gunaratna, Huajun Chen
IJCAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Evaluation results show that our approach significantly outperforms the state of the art on two public benchmarks. |
| Researcher Affiliation | Collaboration | 1National Key Laboratory for Novel Software Technology, Nanjing University, China 2College of Computer Science and Technology, Zhejiang University, China 3Bosch Center for Artificial Intelligence, Robert Bosch Gmb H, Germany 4Department of Informatics, University of Oslo, Norway 5Samsung Research America, Mountain View CA, USA |
| Pseudocode | No | The paper describes its model and approach using mathematical equations and textual descriptions but does not include explicit pseudocode or algorithm blocks. |
| Open Source Code | Yes | 1https://github.com/nju-websoft/NEST |
| Open Datasets | Yes | We evaluated with the two largest available benchmarks for general-purpose entity summarization: the Entity Summarization Bench Mark (ESBM) [Liu et al., 2020] and the FACES Evaluation Dataset (FED) [Gunaratna et al., 2015]. |
| Dataset Splits | Yes | We used 80% of the labeled data for training methods and 20% for validation, e.g., tuning hyperparameters. |
| Hardware Specification | No | The paper does not specify any particular hardware (e.g., GPU, CPU model, memory) used for running the experiments. |
| Software Dependencies | No | The paper mentions "pre-trained fastText embeddings" and various neural network components (LSTMs, MLPs), but it does not provide specific version numbers for any software libraries, frameworks (like TensorFlow or PyTorch), or programming languages used for implementation. |
| Experiment Setup | Yes | Our LSTMs contained 4,096 units, 300 dimension projections, and a residual connection from the first layer to the second layer. We trained for 10 epochs with batch size 256. From each labeled entity description D(e), we randomly sampled 5 triples as a batch and we sampled |D(e)|/2 times. Our MLP had 4,096 units in each layer and applied ReLU activations. We trained for 10 epochs. Our MLP had 4,096 units in each layer and applied ReLU activations. We trained for 10 epochs with batch size 5. In simulated annealing, we initialized the acceptance probability to 0.1, and decreased it by 0.1/|D(e)| after each iteration. |