arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2204.07835cs.CLcs.LG
收藏

假设:生成代码来回答模拟问题

What If: Generating Code to Answer Simulation Questions

Technion(以色列理工学院);Israel Institute of Technology(以色列理工学院)

Gal Peretz, Kira Radinsky

摘要:

许多文本,特别是化学和生物学,描述复杂的过程。我们专注于描述化学反应过程的文本,以及在不同环境条件下询问该过程结果的问题。要回答有关此类流程的问题,需要了解流程中涉及的不同实体之间的交互,并在不同条件下模拟流程执行期间的状态转换。状态转换被定义为程序在执行期间对变量所做的内存修改。我们假设生成代码并执行它来模拟流程将允许回答这些问题。因此,我们定义了一个领域特定语言(DSL)来表示流程。我们为社区贡献了一个由化学家策划并由计算机科学家注释的独特数据集。该数据集由过程文本、模拟问题及其对应的DSL代码组成,提出了一种基于强化学习的神经程序合成方法。新的奖励是基于预测代码和参考代码之间的运行时语义相似性。这允许模拟复杂的过程转换,从而回答模拟问题。我们的方法产生了显着提高模拟问题的准确性:88\%的准确性,而不是83\%的准确性的最先进的神经程序合成方法和54\%的准确性的最先进的端到端的基于文本的方法。

英文摘要:

Many texts, especially in chemistry and biology, describe complex processes. We focus on texts that describe a chemical reaction process and questions that ask about the process's outcome under different environmental conditions. To answer questions about such processes, one needs to understand the interactions between the different entities involved in the process and to simulate their state transitions during the process execution under different conditions. A state transition is defined as the memory modification the program does to the variables during the execution. We hypothesize that generating code and executing it to simulate the process will allow answering such questions. We, therefore, define a domain-specific language (DSL) to represent processes. We contribute to the community a unique dataset curated by chemists and annotated by computer scientists. The dataset is composed of process texts, simulation questions, and their corresponding computer codes represented by the DSL.We propose a neural program synthesis approach based on reinforcement learning with a novel state-transition semantic reward. The novel reward is based on the run-time semantic similarity between the predicted code and the reference code. This allows simulating complex process transitions and thus answering simulation questions. Our approach yields a significant boost in accuracy for simulation questions: 88\% accuracy as opposed to 83\% accuracy of the state-of-the-art neural program synthesis approaches and 54\% accuracy of state-of-the-art end-to-end text-based approaches.

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。

↑