论文标题
用于从用户互动中学习语义解析器的模仿游戏
An Imitation Game for Learning Semantic Parsers from User Interaction
论文作者
论文摘要
尽管应用程序取得了广泛的成功，但引导和微调语义解析器仍然是一个乏味的过程，诸如昂贵的数据注释和隐私风险等挑战。在本文中，我们建议一种直接从用户学习语义解析器的替代性，人为的方法。语义解析器应内省其不确定性，并在不确定时提示用户演示。这样一来，它也可以模仿用户行为并继续自主改善自己，希望最终它可能与用户解释其问题一样好。为了打击示范的稀疏性，我们提出了一种新颖的注释效率的模仿学习算法，该算法通过混合示范状态和自信的预测并以数据集聚合方式重新培训语义解析器来迭代地收集新数据集（Ross等，2011）。我们对其成本约束的理论分析进行了理论分析，并在经验上证明了其在文本到SQL问题上的有希望的表现。代码将在https://github.com/sunlab-osu/misp上找到。
Despite the widely successful applications, bootstrapping and fine-tuning semantic parsers are still a tedious process with challenges such as costly data annotation and privacy risks. In this paper, we suggest an alternative, human-in-the-loop methodology for learning semantic parsers directly from users. A semantic parser should be introspective of its uncertainties and prompt for user demonstration when uncertain. In doing so it also gets to imitate the user behavior and continue improving itself autonomously with the hope that eventually it may become as good as the user in interpreting their questions. To combat the sparsity of demonstration, we propose a novel annotation-efficient imitation learning algorithm, which iteratively collects new datasets by mixing demonstrated states and confident predictions and re-trains the semantic parser in a Dataset Aggregation fashion (Ross et al., 2011). We provide a theoretical analysis of its cost bound and also empirically demonstrate its promising performance on the text-to-SQL problem. Code will be available at https://github.com/sunlab-osu/MISP.
