2018/11/07 by Koustuv Sinha, Shagun Sodhani, Sinha, Koustuv +6
Computer Science · #Multi-Agent Systems and Negotiation #Natural Language Processing Techniques #Topic Modeling #cs.AI #cs.CL
paper · pdf · doi:10.48550/arxiv.1811.02959
4 pages of main content, to be presented at Relational Representation Learning Workshop, NIPS 2018, Montreal
arxiv created 2018/11/08 · arxiv updated 2018/11/09
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.