arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2110.03323cs.CL
收藏

基于逻辑的荷兰语自然语言推理框架

A Logic-Based Framework for Natural Language Inference in Dutch

Utrecht University(乌得勒支大学)

Lasha Abzianidze, Konstantinos Kogkalidis

摘要:

我们提出了一个框架推导荷兰句子对之间的推理关系。所提出的框架依赖于基于逻辑的推理,以产生可检查的证据,导致推理标签,因此,它的判断是透明的,形式上可验证的。该系统的核心是由两个$λ$ -演算提供支持,分别用作语法和语义理论。句子首先被转换为语法证明和线性$λ$演算的术语,使用两个解析器的选择:基于Alpino的管道和神经证明网络。然后,通过一组手工设计的类型和术语级转换,将语法术语转换为简单类型化的$λ$ -演算的语义术语。然后,将成对的语义术语输入到自然逻辑的自动定理证明器,该自动定理证明器在使用Open Dutch WordNet中找到的词汇关系的同时对它们进行推理。我们在最近创建的荷兰自然语言推理数据集上评估了推理管道,并取得了令人鼓舞的结果,仅在强神经基线的$1.1-3.2{\%}$性能裕度内保持。据我们所知,推理管道是荷兰语的第一个基于逻辑的系统。

英文摘要:

We present a framework for deriving inference relations between Dutch sentence pairs. The proposed framework relies on logic-based reasoning to produce inspectable proofs leading up to inference labels; its judgements are therefore transparent and formally verifiable. At its core, the system is powered by two $λ$-calculi, used as syntactic and semantic theories, respectively. Sentences are first converted to syntactic proofs and terms of the linear $λ$-calculus using a choice of two parsers: an Alpino-based pipeline, and Neural Proof Nets. The syntactic terms are then converted to semantic terms of the simply typed $λ$-calculus, via a set of hand designed type- and term-level transformations. Pairs of semantic terms are then fed to an automated theorem prover for natural logic which reasons with them while using the lexical relations found in the Open Dutch WordNet. We evaluate the reasoning pipeline on the recently created Dutch natural language inference dataset, and achieve promising results, remaining only within a $1.1-3.2{\%}$ performance margin to strong neural baselines. To the best of our knowledge, the reasoning pipeline is the first logic-based system for Dutch.

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。

↑