# DyKGChat **Repository Path**: xubinlee/DyKGChat ## Basic Information - **Project Name**: DyKGChat - **Description**: for of https://gitee.com/feiwangyuzhou/DyKGChat - **Primary Language**: Unknown - **License**: Not specified - **Default Branch**: master - **Homepage**: None - **GVP Project**: No ## Statistics - **Stars**: 0 - **Forks**: 0 - **Created**: 2020-11-05 - **Last Updated**: 2020-12-19 ## Categories & Tags **Categories**: Uncategorized **Tags**: None ## README # DyKGChat The project contains the collected data and code of our paper [**Yi-Lin Tuan, Yun-Nung Chen, Hung-yi Lee. "DyKgChat: Benchmarking Dialogue Generation Grounding on Dynamic Knowledge Graphs", EMNLP 2019**](https://arxiv.org/abs/1910.00610). The extended abstract version is called **Dynamic Knowledge-Grounded Dialogue Generation through Walking on the Graph**. * our proposed approach: (Qadpt) **Q**uick **Ad**a**pt**ive Dynamic Knoledge-Grounded Neural Converation Model (pronouce: Q-adapt) ![Qadpt](Qadpt_model.png) ## Setup ### Installation (my environment) * python3.6 * tensorflow r1.13 * jieba * nltk3.2.5 ### Files * `data/`: the collected data `hgzhz/` and `friends/` as well as the trained TransE * `model_ckpts/`: the trained models in the paper ## Usage * clone the repository * run the script `run.sh` ``` $bash run.sh ``` * for , check your device avalibility by `nvidia-smi` * for , choose from `train`, `pred_acc`, `eval_pred_acc`, `ifchange` * for , choose from `seq2seq`, `MemNet`, `TAware`, `KAware`, `Qadpt` * for , choose from `friends`, `hgzhz_v1_0`(used in our paper), `hgzhz`(current newest version) * for , check the directory `model_ckpts` ## More description * testing method * `pred_acc`: for metrics `Generated-KW`, `BLEU-2`, `distinct-n` * `eval_pred_acc`: for metrics `KW-Acc`, `KW/Generic`, `perplexity` * `ifchange`: for change rates / accurate change rates * script options * the `hops_num` and `change_level` are required to be changed in `run.sh`