论文标题
与您的解析器交谈：与自然语言反馈的交互式文本到SQL
Speak to your Parser: Interactive Text-to-SQL with Natural Language Feedback
论文作者
论文摘要
我们研究语义解析校正的任务，并使用自然语言反馈。鉴于自然语言的话语，大多数语义解析系统构成了一个问题翻译，其中讲述被映射到相应的逻辑形式。在本文中，我们调查了一个更具交互性的场景，其中人类可以通过提供自由形式的自然语言反馈来进一步与系统进行交互，以纠正系统对初始话语的不准确解释。我们专注于SQL系统的自然语言和构造，飞溅，话语数据集，不正确的SQL解释以及相应的自然语言反馈。我们比较了校正任务的各种参考模型，并表明纳入如此丰富的反馈形式可以显着提高整体语义解析精度，同时保持自然语言互动的灵活性。虽然我们估计人类校正精度为81.5％，但我们的最佳模型只能达到25.1％，这在未来的研究中留下了很大的差距。 Splash可在https://aka.ms/splash_dataset上公开获取。
We study the task of semantic parse correction with natural language feedback. Given a natural language utterance, most semantic parsing systems pose the problem as one-shot translation where the utterance is mapped to a corresponding logical form. In this paper, we investigate a more interactive scenario where humans can further interact with the system by providing free-form natural language feedback to correct the system when it generates an inaccurate interpretation of an initial utterance. We focus on natural language to SQL systems and construct, SPLASH, a dataset of utterances, incorrect SQL interpretations and the corresponding natural language feedback. We compare various reference models for the correction task and show that incorporating such a rich form of feedback can significantly improve the overall semantic parsing accuracy while retaining the flexibility of natural language interaction. While we estimated human correction accuracy is 81.5%, our best model achieves only 25.1%, which leaves a large gap for improvement in future research. SPLASH is publicly available at https://aka.ms/Splash_dataset.
