SGD-X: A Benchmark for Robust Generalization in Schema-Guided Dialogue Systems
Abstract
Zero/few-shot transfer to unseen services is a critical challenge in task-oriented dialogue research. The Schema-Guided Dialogue (SGD) dataset introduced a paradigm for enabling models to support any service in zero-shot through schemas, which describe service APIs to models in natural language. We explore the robustness of dialogue systems to linguistic variations in schemas by designing SGD-X - a benchmark extending SGD with semantically similar yet stylistically diverse variants for every schema. We observe that two top state tracking models fail to generalize well across schema variants, measured by joint goal accuracy and a novel metric for measuring schema sensitivity. Additionally, we present a simple model-agnostic data augmentation method to improve schema robustness.
Cite
Text
Lee et al. "SGD-X: A Benchmark for Robust Generalization in Schema-Guided Dialogue Systems." AAAI Conference on Artificial Intelligence, 2022. doi:10.1609/AAAI.V36I10.21341Markdown
[Lee et al. "SGD-X: A Benchmark for Robust Generalization in Schema-Guided Dialogue Systems." AAAI Conference on Artificial Intelligence, 2022.](https://mlanthology.org/aaai/2022/lee2022aaai-sgd/) doi:10.1609/AAAI.V36I10.21341BibTeX
@inproceedings{lee2022aaai-sgd,
title = {{SGD-X: A Benchmark for Robust Generalization in Schema-Guided Dialogue Systems}},
author = {Lee, Harrison and Gupta, Raghav and Rastogi, Abhinav and Cao, Yuan and Zhang, Bin and Wu, Yonghui},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2022},
pages = {10938-10946},
doi = {10.1609/AAAI.V36I10.21341},
url = {https://mlanthology.org/aaai/2022/lee2022aaai-sgd/}
}