A Deep Neural Network for Chinese Zero Pronoun Resolution
Authors: Qingyu Yin, Weinan Zhang, Yu Zhang, Ting Liu
IJCAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We conduct experiments on the Chinese portion of the Onto Notes 5.0 corpus. Experimental results show that our approach substantially outperforms the state-of-the-art method in various experimental settings. |
| Researcher Affiliation | Academia | Research Center for Social Computing and Information Retrieval Harbin Institute of Technology, China {qyyin, wnzhang, yzhang, tliu}@ir.hit.edu.cn |
| Pseudocode | No | The paper provides a diagram of the Zero Pronoun-specific Neural Network (ZPSNN) in Figure 1, and describes the model components in text, but it does not include any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not include an explicit statement that the authors' source code for the described methodology is publicly available, nor does it provide a direct link to a code repository. |
| Open Datasets | Yes | We employ the dataset used in the official Co NLL-2012 shared task, from the Onto Notes Release 5.0, to carry out our experiment. |
| Dataset Splits | No | The paper states the CoNLL-2012 shared task dataset consists of 'a training set, a development set, and a test set'. However, it explicitly states 'we thus utilize the training set for training and the development set for testing,' without mentioning a separate validation split for hyperparameter tuning. |
| Hardware Specification | No | The paper describes the experimental setup and results but does not provide any specific details about the hardware used, such as CPU or GPU models, or memory specifications. |
| Software Dependencies | No | The paper mentions using 'word2vec toolkit' and 'Berkeley parser' for parts of the pipeline, but it does not provide specific version numbers for these or any other software dependencies, which would be required for reproducibility. |
| Experiment Setup | Yes | We take the derivative of loss function through backpropagation with respect to the whole set of parameters, and update parameters with stochastic gradient descent by setting the learning rate as 0.01. We use a pre-trained 100dimensional Chinese word embeddings as inputs. For parameters, we randomly initialize them from a uniform distribution U( 0.01, 0.01). |