DialogVCS：对话系统升级中鲁棒的自然语言理解
DialogVCS: Robust Natural Language Understanding in Dialogue System Upgrade
AI总结：
本文针对对话系统更新中新旧意图产生语义纠缠损害NLU模型鲁棒性的问题，提出DialogVCS基准，将意图检测表述为正但未标记的多标签分类任务，并证明自动工作流能有效识别语义纠缠的意图。
摘要：
在产品对话系统的持续更新中，我们需要重新训练自然语言理解（NLU）模型，因为来自真实用户的新数据会被合并到上次更新中积累的现有数据中。在新增数据中，会出现新意图，并可能与现有意图产生语义纠缠，例如，在语义空间中语义过于具体或宽泛的新意图实际上是一些现有意图的子集或超集，从而损害NLU模型的鲁棒性。作为解决此问题的首次尝试，我们建立了一个由4个对话版本控制数据集（DialogVCS）组成的新基准。我们将系统更新中存在不完美数据的意图检测表述为具有正但未标记意图的多标签分类任务，要求模型在推理时识别所有合适的意图，包括存在语义纠缠的意图。我们还提出了综合基线模型，并对该基准进行了深入分析，表明通过自动工作流可以有效识别语义纠缠的意图。
英文摘要：
In the constant updates of the product dialogue systems, we need to retrain the natural language understanding (NLU) model as new data from the real users would be merged into the existent data accumulated in the last updates. Within the newly added data, new intents would emerge and might have semantic entanglement with the existing intents, e.g. new intents that are semantically too specific or generic are actually subset or superset of some existing intents in the semantic space, thus impairing the robustness of the NLU model. As the first attempt to solve this problem, we setup a new benchmark consisting of 4 Dialogue Version Control dataSets (DialogVCS). We formulate the intent detection with imperfect data in the system update as a multi-label classification task with positive but unlabeled intents, which asks the models to recognize all the proper intents, including the ones with semantic entanglement, in the inference. We also propose comprehensive baseline models and conduct in-depth analyses for the benchmark, showing that the semantically entangled intents can be effectively recognized with an automatic workflow.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
