Infobox-to-text Generation with Tree-like Planning based Attention Network
Authors: Yang Bai, Ziran Li, Ning Ding, Ying Shen, Hai-Tao Zheng
IJCAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We conduct sets of experiments on two real-world datasets, which aim to generate a textual description of a person (or restaurant) from a given infobox. The experimental results show that our model outperforms state-of-the-art methods on automatic evaluation metrics and has better adaptability to disordered input. We also implement qualitative human evaluation to further estimate the quality of our model. |
| Researcher Affiliation | Academia | 1Department of Computer Science and Technology, Tsinghua University 2Tsinghua Shen Zhen International Graduate School, Tsinghua University 3School of Intelligent Systems Engineering, Sun Yat-Sen University {bai-y18, lizr18}@mails.tsinghua.edu.cn |
| Pseudocode | No | The paper describes its methodology in text and with architectural diagrams, but does not include explicit pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide any explicit statement or link indicating that the source code for the described methodology is publicly available. |
| Open Datasets | Yes | We conduct experiments on two datasets: (1) WIKIBIO aims to generate the first sentence of a biography from a given Wikipedia infobox. (2) E2E [Novikova et al., 2017] aims to generate descriptions of restaurants from dialogue act-based meaning representations. |
| Dataset Splits | No | The paper mentions training on datasets but does not explicitly provide details about validation dataset splits, such as percentages, sample counts, or specific methods for creating the split. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used for running the experiments, such as GPU or CPU models. |
| Software Dependencies | No | The paper does not provide specific version numbers for software dependencies or libraries used in the experiments. |
| Experiment Setup | Yes | During experiments we set the dimension of word vectors and hidden state dw = 300 and the number of heads H = 6. We choose the most frequent 30, 000 words in the training set as the vocabulary of WIKIBIO. A copy mechanism is applied to replace the unknown words UNK with the most likely word in the input data according to the attention distribution. We train the two stages separately for 10 epochs then jointly for 40 epochs. During joint training we set λ = 0.4. |