DialoKG
1.0.0
พื้นที่เก็บข้อมูลนี้มีรหัส pytorch สำหรับ NAACL 2022 Paper: Dialokg: โครงสร้างความรู้รู้ถึงการสร้างบทสนทนาที่มุ่งเน้นงาน [PDF]
conda create -n dialokg -y python=3.7 && source activate dialokg
pip install -r requirements.txt
chmod +x setup.sh
./setup.sh
# training using a single gpu
python train.py --dataset < DATASET-NAME > --params_file config/gpt2/params.json --device cuda
# training in a distributed setting
python -m torch.distributed.launch --dataset < DATASET-NAME > --params_file config/gpt2/params.json --device cudaชื่อชุดข้อมูลที่ถูกต้อง: Incar , Camrest , Woz2.1
python eval.py --generate runs/dialokg-gpt2/ < DATASET-NAME > --dataset < DATASET-NAME > --generation_params_file config/gpt2/generation_params.json --eval_dataset test --output_file outputs/ < DATASET-NAME > -output.json --top_weights 7โปรดทราบว่า:
@inproceedings{rony-etal-2022-dialokg,
title = "{D}ialo{KG}: Knowledge-Structure Aware Task-Oriented Dialogue Generation",
author = "Rony, Md Rashad Al Hasan and
Usbeck, Ricardo and
Lehmann, Jens",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2022",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-naacl.195",
pages = "2557--2571",
abstract = "Task-oriented dialogue generation is challenging since the underlying knowledge is often dynamic and effectively incorporating knowledge into the learning process is hard. It is particularly challenging to generate both human-like and informative responses in this setting. Recent research primarily focused on various knowledge distillation methods where the underlying relationship between the facts in a knowledge base is not effectively captured. In this paper, we go one step further and demonstrate how the structural information of a knowledge graph can improve the system{'}s inference capabilities. Specifically, we propose DialoKG, a novel task-oriented dialogue system that effectively incorporates knowledge into a language model. Our proposed system views relational knowledge as a knowledge graph and introduces (1) a structure-aware knowledge embedding technique, and (2) a knowledge graph-weighted attention masking strategy to facilitate the system selecting relevant information during the dialogue generation. An empirical evaluation demonstrates the effectiveness of DialoKG over state-of-the-art methods on several standard benchmark datasets.",
}
มิกซ์
สำหรับข้อมูลเพิ่มเติมติดต่อผู้เขียน MD Rashad Al Hasan Rony (อีเมล) ที่เกี่ยวข้อง