本文提出了一个框架，可以通过以解释为中心的语料库来重构对多项选择科学问题的解释。该框架以科学统一的概念为基础，通过结合两个不同的分数，对有关问题和候选答案的解释性事实进行排名：（a）关联度（RS），表示给定事实在特定程度上的程度这个问题（b）统一分数（美国），该分数考虑了事实的解释力，该事实的解释力是根据对类似问题的解释中出现的频率确定的。在Worldtree语料库上对该框架进行了广泛的评估，并采用IR加权方案对其实施。提出以下发现：（1）与最先进的变压器相比，所提出的方法取得了竞争性结果，但具有可扩展到大型解释性知识库的特性； （2）组合模型明显优于IR基准（+ 7.8 / 8.4 MAP），证实了相关性和统一评分的互补方面； （3）构建的解释可以支持下游模型进行答案预测，从而提高ARC轻松（+ 6.92％）和挑战（+ 15.69％）问题上多项选择QA的BERT的准确性。
原文标题：Unification-based Reconstruction of Explanations for Science Questions
原文：The paper presents a framework to reconstruct explanations for multiple choices science questions through explanation-centred corpora. Building upon the notion of unification in science, the framework ranks explanatory facts with respect to question and candidate answer by leveraging a combination of two different scores: (a) A Relevance Score (RS) that represents the extent to which a given fact is specific to the question; (b) A Unification Score (US) that takes into account the explanatory power of a fact, determined according to its frequency in explanations for similar questions. An extensive evaluation of the framework is performed on the Worldtree corpus, adopting IR weighting schemes for its implementation. The following findings are presented: (1) The proposed approach achieves competitive results when compared to state-of-the-art Transformers, yet possessing the property of being scalable to large explanatory knowledge bases; (2) The combined model significantly outperforms IR baselines (+7.8/8.4 MAP), confirming the complementary aspects of relevance and unification score; (3) The constructed explanations can support downstream models for answer prediction, improving the accuracy of BERT for multiple choices QA on both ARC easy (+6.92%) and challenge (+15.69%) questions.
原文作者：Marco Valentino, Mokanarangan Thayaparan, André Freitas
原文地址：https://arxiv.org/abs/2004.00061
基于统一的科学问题解释的重构(CS.AI).pdf