arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2311.01161cs.CLcs.AI
收藏

基于执行的虚假程序过滤的弱监督语义解析

Weakly Supervised Semantic Parsing with Execution-based Spurious Program Filtering

Seoul National University(首尔大学);Samsung Electronics Mobile eXperience(三星电子移动体验)

Kang-il Lee, Segwang Kim, Kyomin Jung

AI总结:

针对弱监督语义解析中的虚假程序问题,提出基于多输入执行结果表示与多数投票的领域无关过滤机制,可正交增强现有框架并显著提升性能。

摘要:

在从弱监督中训练语义解析器时,虚假程序问题是一项长期存在的挑战。为了消除这些语义错误但指称正确的程序,现有方法侧重于利用基于领域特定知识的样本间相似性。本文提出一种基于程序执行结果的领域无关过滤机制。具体而言,对于搜索过程中得到的每个程序,我们首先构建一种表示,将该程序的语义刻画为其在各种输入下的执行结果。随后,我们对这些表示进行多数投票,以识别并过滤掉语义与其他程序显著不同的程序。特别地,我们的方法与程序搜索过程相互正交,因此可以轻松增强任何现有弱监督语义解析框架。在 Natural Language Visual Reasoning 和 WikiTableQuestions 上的实证评估表明,将该方法应用于现有语义解析器可带来显著的性能提升。

英文摘要:

The problem of spurious programs is a longstanding challenge when training a semantic parser from weak supervision. To eliminate such programs that have wrong semantics but correct denotation, existing methods focus on exploiting similarities between examples based on domain-specific knowledge. In this paper, we propose a domain-agnostic filtering mechanism based on program execution results. Specifically, for each program obtained through the search process, we first construct a representation that captures the program's semantics as execution results under various inputs. Then, we run a majority vote on these representations to identify and filter out programs with significantly different semantics from the other programs. In particular, our method is orthogonal to the program search process so that it can easily augment any of the existing weakly supervised semantic parsing frameworks. Empirical evaluations on the Natural Language Visual Reasoning and WikiTableQuestions demonstrate that applying our method to the existing semantic parsers induces significantly improved performances.

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。

↑