Improving Dialogue Intent Classification with a Knowledge-Enhanced Multifactor Graph Model (Student Abstract)
Abstract
Although current Graph Neural Network (GNN) based models achieved good performances in Dialogue Intent Classification (DIC), they leaf the inherent domain-specific knowledge out of consideration, leading to the lack of ability of acquiring fine-grained semantic information. In this paper, we propose a Knowledge-Enhanced Multifactor Graph (KEMG) Model for DIC. We firstly present a knowledge-aware utterance encoder with the help of a domain-specific knowledge graph, fusing token-level and entity-level semantic information, then design a heterogeneous dialogue graph encoder by explicitly modeling several factors that matter to contextual modeling of dialogues. Experiment results show that our proposed method outperforms other GNN-based methods on a dataset collected from a real-world online customer service dialogue system on the e-commerce website, JD.
Cite
Text
Xu et al. "Improving Dialogue Intent Classification with a Knowledge-Enhanced Multifactor Graph Model (Student Abstract)." AAAI Conference on Artificial Intelligence, 2023. doi:10.1609/AAAI.V37I13.27043Markdown
[Xu et al. "Improving Dialogue Intent Classification with a Knowledge-Enhanced Multifactor Graph Model (Student Abstract)." AAAI Conference on Artificial Intelligence, 2023.](https://mlanthology.org/aaai/2023/xu2023aaai-improving-a/) doi:10.1609/AAAI.V37I13.27043BibTeX
@inproceedings{xu2023aaai-improving-a,
title = {{Improving Dialogue Intent Classification with a Knowledge-Enhanced Multifactor Graph Model (Student Abstract)}},
author = {Xu, Huinan and Pang, Jinhui and Song, Shuangyong and Zou, Bo},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2023},
pages = {16366-16367},
doi = {10.1609/AAAI.V37I13.27043},
url = {https://mlanthology.org/aaai/2023/xu2023aaai-improving-a/}
}