Adversarial Mutual Information for Text Generation
Authors: Boyuan Pan, Yazheng Yang, Kaizhao Liang, Bhavya Kailkhura, Zhongming Jin, Xian-Sheng Hua, Deng Cai, Bo Li
ICML 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments based on different text generation tasks demonstrate that the proposed AMI framework can significantly outperform several strong baselines, and we also show that AMI has potential to lead to a tighter lower bound of maximum mutual information for the variational information maximization problem. |
| Researcher Affiliation | Collaboration | 1State Key Lab of CAD&CG, Zhejiang University 2College of Computer Science, Zhejiang University 3University of Illinois Urbana-Champaign 4Lawrence Livermore National Laboratory 5Alibaba Group. |
| Pseudocode | No | The paper does not contain structured pseudocode or algorithm blocks. |
| Open Source Code | Yes | Code is available at https://github.com/ZJULearning/AMI. |
| Open Datasets | Yes | We evaluate our dialog model on the Persona Chat dataset (Zhang et al., 2018a). The dataset for our evaluation is the WMT translation task between English and German in both directions and the translation performances are reported on the official test set newstest2014. |
| Dataset Splits | Yes | There are around 160,000 utterances in around 11,000 dialogues, with 2000 dialogues for validation and test, which use non-overlapping personas. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., GPU/CPU models, memory amounts) used for running its experiments. |
| Software Dependencies | No | The paper does not provide specific software dependency details with version numbers (e.g., Python 3.8, PyTorch 1.9). |
| Experiment Setup | Yes | Detailed configurations are in the Appendix B.1. Detailed configurations are in the Appendix B.2. |