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 2106.01354cs.CLcs.AIcs.LGcs.LO
收藏

multiPRover:生成多个证明以提高规则推理的可解释性

multiPRover: Generating Multiple Proofs for Improved Interpretability in Rule Reasoning

UNC Chapel Hill(北卡罗来纳大学教堂山分校)

Swarnadeep Saha, Prateek Yadav, Mohit Bansal

摘要:

我们专注于一种语言形式推理,其目标是以自然语言事实和规则的形式对显式知识进行推理(Clark等人,2020年)。最近的一项工作,名为PRover(Saha等人,2020)通过回答问题并生成解释答案的证明图来执行这种推理。然而,组合推理并不总是唯一的,可能有多种方法可以达到正确的答案。因此,在我们的工作中,我们解决了一个新的和具有挑战性的问题,产生多个证明图推理的自然语言规则库。每个证明都为答案提供了不同的理由,从而提高了这种推理系统的可解释性。为了共同学习所有的证明图,并利用一个问题的多个证明之间的相关性,我们把这个任务作为一个集生成问题的结构化输出空间,其中每个证明表示为一个有向图。我们提出了两个变种的证明集生成模型,multiPR。我们的第一个模型,Multilabel-multiPRover,通过多标签分类和隐式条件之间的证明生成一组证明;而第二个模型,迭代-multiPRover,通过显式条件迭代地生成证明先前生成的证明。在多个合成、zero-shot和人类释义数据集上的实验表明,这两个multiPRover模型在包含多个黄金证据的数据集上的性能显著优于PRover。Iterative-multiPR over在所有示例只有一个正确证明的zero-shot场景中获得最先进的证明F1。它还可以更好地推广到需要更高推理深度的问题,其中多个证明更频繁。我们的代码和模型可在https://github.com/swarnaHub/multiPRover上公开获取

英文摘要:

We focus on a type of linguistic formal reasoning where the goal is to reason over explicit knowledge in the form of natural language facts and rules (Clark et al., 2020). A recent work, named PRover (Saha et al., 2020), performs such reasoning by answering a question and also generating a proof graph that explains the answer. However, compositional reasoning is not always unique and there may be multiple ways of reaching the correct answer. Thus, in our work, we address a new and challenging problem of generating multiple proof graphs for reasoning over natural language rule-bases. Each proof provides a different rationale for the answer, thereby improving the interpretability of such reasoning systems. In order to jointly learn from all proof graphs and exploit the correlations between multiple proofs for a question, we pose this task as a set generation problem over structured output spaces where each proof is represented as a directed graph. We propose two variants of a proof-set generation model, multiPRover. Our first model, Multilabel-multiPRover, generates a set of proofs via multi-label classification and implicit conditioning between the proofs; while the second model, Iterative-multiPRover, generates proofs iteratively by explicitly conditioning on the previously generated proofs. Experiments on multiple synthetic, zero-shot, and human-paraphrased datasets reveal that both multiPRover models significantly outperform PRover on datasets containing multiple gold proofs. Iterative-multiPRover obtains state-of-the-art proof F1 in zero-shot scenarios where all examples have single correct proofs. It also generalizes better to questions requiring higher depths of reasoning where multiple proofs are more frequent. Our code and models are publicly available at https://github.com/swarnaHub/multiPRover

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。

↑