Optimizing NLU Reranking Using Entity Resolution Signals in Multi-domain Dialog Systems
Tong Wang, Jiangning Chen, Mohsen Malmir, Shuyan Dong, Xin He, Han Wang, Chengwei Su, Yue Liu
Abstract
In dialog systems, the Natural Language Understanding (NLU) component typically makes the interpretation decision (including domain, intent and slots) for an utterance before the mentioned entities are resolved. This may result in intent classification and slot tagging errors. In this work, we propose to leverage Entity Resolution (ER) features in NLU reranking and introduce a novel loss term based on ER signals to better learn model weights in the reranking framework. In addition, for a multi-domain dialog scenario, we propose a score distribution matching method to ensure scores generated by the NLU reranking models for different domains are properly calibrated. In offline experiments, we demonstrate our proposed approach significantly outperforms the baseline model on both single-domain and cross-domain evaluations.
BibTeX
@inproceedings{wang-etal-2021-optimizing,
title = "Optimizing {NLU} Reranking Using Entity Resolution Signals in Multi-domain Dialog Systems",
author = "Wang, Tong and
Chen, Jiangning and
Malmir, Mohsen and
Dong, Shuyan and
He, Xin and
Wang, Han and
Su, Chengwei and
Liu, Yue and
Liu, Yang",
editor = "Kim, Young-bum and
Li, Yunyao and
Rambow, Owen",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Papers",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-industry.3/",
doi = "10.18653/v1/2021.naacl-industry.3",
pages = "19--25"
}