arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.12638cs.PLcs.AI
收藏

信息论用户交互:程序合成的重要输入

Information-theoretic User Interaction: Significant Inputs for Program Synthesis

Microsoft(微软)

Ashish Tiwari, Arjun Radhakrishna, Sumit Gulwani, Daniel Perelman

摘要:

示例编程技术正在工业产品中部署,用于实时合成各种数据转换。这些技术依赖于用户提供转换任务的几个代表性示例。出于需要找到最相关的问题问用户,在本文中,我们介绍了{ \em重要问题的问题},并表明它是很难在一般情况下。然后,我们开发了一个信息理论贪婪的方法来解决这个问题。我们证明贪心算法使用条件熵的结果,这非正式地说,实现最大的信息增益的问题是一个我们知道的最少。在交互式程序合成的上下文中,我们使用上述结果来开发{ \em{active program learner} },该{ \em{active program learner} }在每次迭代中生成重要的输入以作为对用户的查询。该过程需要将{ \em{passive program learner} }扩展为{ \em{sampling program learner} },该{ \em{sampling program learner} }能够从所有一致程序的集合中对候选程序进行采样以使得能够估计信息增益。它还使用基于输入和相应输出中的特征的输入聚类来对一小组候选重要输入进行采样。我们的主动学习器能够权衡假阴性和假阳性,并在真实世界的数据集上进行少量迭代收敛,数据集大约有800个字符串转换任务。

英文摘要:

Programming-by-example technologies are being deployed in industrial products for real-time synthesis of various kinds of data transformations. These technologies rely on the user to provide few representative examples of the transformation task. Motivated by the need to find the most pertinent question to ask the user, in this paper, we introduce the {\em significant questions problem}, and show that it is hard in general. We then develop an information-theoretic greedy approach for solving the problem. We justify the greedy algorithm using the conditional entropy result, which informally says that the question that achieves the maximum information gain is the one that we know least about. In the context of interactive program synthesis, we use the above result to develop an {\em{active program learner}} that generates the significant inputs to pose as queries to the user in each iteration. The procedure requires extending a {\em{passive program learner}} to a {\em{sampling program learner}} that is able to sample candidate programs from the set of all consistent programs to enable estimation of information gain. It also uses clustering of inputs based on features in the inputs and the corresponding outputs to sample a small set of candidate significant inputs. Our active learner is able to tradeoff false negatives for false positives and converge in a small number of iterations on a real-world dataset of %around 800 string transformation tasks.

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。

↑