arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1811.08048cs.CL
收藏

QuaRel:一个定性关系问题的数据集和模型

QuaRel: A Dataset and Models for Answering Questions about Qualitative Relationships

Allen Institute for AI(艾伦人工智能研究所)

Oyvind Tafjord, Peter Clark, Matt Gardner, Wen-tau Yih, Ashish Sabharwal

摘要:

许多自然语言问题需要利用定性关系(例如,在科学、经济学和医学中),但是用基于语料库的方法来回答是具有挑战性的。定性建模提供了支持这种推理的工具,但是将问题映射到这些模型的语义解析任务具有巨大的挑战。我们提出了一个包含不同故事问题的数据集,涉及表征这些挑战的定性关系,以及开始解决这些问题的技术。该数据集有2771个问题,涉及19种不同类型的数量。例如,“珍妮观察到,机器人吸尘器在客厅地毯上的移动速度比在卧室地毯上慢。哪种地毯的摩擦力更大?“我们贡献了(1)一个简单而灵活的概念框架来表示这类问题;(2)包含逻辑形式的Rel数据集,举例说明了解析挑战;(3)针对这一任务的两个新模型,作为类型约束语义解析的扩展而构建。其中第一个模型(称为CNOSP+)的性能明显优于CNORel上的现成工具。第二个(CNOSP +Zero)演示了zero-shot能力,即,处理新的定性关系而不需要额外的训练数据的能力,这在以前的模型中是不可能的。因此,这项工作有助于回答需要推理的复杂定性问题,并以低成本扩展到新的关系。数据集和模型可在http://data.allenai.org/quarel上获得。

英文摘要:

Many natural language questions require recognizing and reasoning with qualitative relationships (e.g., in science, economics, and medicine), but are challenging to answer with corpus-based methods. Qualitative modeling provides tools that support such reasoning, but the semantic parsing task of mapping questions into those models has formidable challenges. We present QuaRel, a dataset of diverse story questions involving qualitative relationships that characterize these challenges, and techniques that begin to address them. The dataset has 2771 questions relating 19 different types of quantities. For example, "Jenny observes that the robot vacuum cleaner moves slower on the living room carpet than on the bedroom carpet. Which carpet has more friction?" We contribute (1) a simple and flexible conceptual framework for representing these kinds of questions; (2) the QuaRel dataset, including logical forms, exemplifying the parsing challenges; and (3) two novel models for this task, built as extensions of type-constrained semantic parsing. The first of these models (called QuaSP+) significantly outperforms off-the-shelf tools on QuaRel. The second (QuaSP+Zero) demonstrates zero-shot capability, i.e., the ability to handle new qualitative relationships without requiring additional training data, something not possible with previous models. This work thus makes inroads into answering complex, qualitative questions that require reasoning, and scaling to new relationships at low cost. The dataset and models are available at http://data.allenai.org/quarel.

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。

↑