Compositional Language Understanding with Text-based Relational Reasoning.pdf

【文件属性】：
文件名称：Compositional Language Understanding with Text-based Relational Reasoning.pdf
文件大小：486KB
文件格式：PDF
更新时间：2023-04-19 04:16:07
NLP Neural networks for natural language reasoning have largely focused on extractive, fact-based question-answering (QA) and common-sense inference. However, it is also crucial to understand the extent to which neural networks can perform relational reasoning and combinatorial generalization from natural language—abilities that are often obscured by annotation artifacts and the dominance of language modeling in standard QA benchmarks. In this work, we present a novel benchmark dataset for language understanding that isolates performance on relational reasoning. We also present a neural message-passing baseline and show that this model, which incorporates a relational inductive bias, is superior at combinatorial generalization compared to a traditional recurrent neural network approach.