Description-Driven Task-Oriented Dialog Modeling [article]

Jeffrey Zhao, Raghav Gupta, Yuan Cao, Dian Yu, Mingqiu Wang, Harrison Lee, Abhinav Rastogi, Izhak Shafran, Yonghui Wu
<span title="2022-01-21">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Task-oriented dialogue (TOD) systems are required to identify key information from conversations for the completion of given tasks. Such information is conventionally specified in terms of intents and slots contained in task-specific ontology or schemata. Since these schemata are designed by system developers, the naming convention for slots and intents is not uniform across tasks, and may not convey their semantics effectively. This can lead to models memorizing arbitrary patterns in data,
more &raquo; ... lting in suboptimal performance and generalization. In this paper, we propose that schemata should be modified by replacing names or notations entirely with natural language descriptions. We show that a language description-driven system exhibits better understanding of task specifications, higher performance on state tracking, improved data efficiency, and effective zero-shot transfer to unseen tasks. Following this paradigm, we present a simple yet effective Description-Driven Dialog State Tracking (D3ST) model, which relies purely on schema descriptions and an "index-picking" mechanism. We demonstrate the superiority in quality, data efficiency and robustness of our approach as measured on the MultiWOZ (Budzianowski et al.,2018), SGD (Rastogi et al., 2020), and the recent SGD-X (Lee et al., 2021) benchmarks.
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2201.08904v1">arXiv:2201.08904v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wzzw6xc4o5cp5ndxmoir4upv64">fatcat:wzzw6xc4o5cp5ndxmoir4upv64</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220129022109/https://arxiv.org/pdf/2201.08904v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/7e/fb/7efb1788b5e0fa3b4d9932722286ba1753b42f91.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2201.08904v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>