arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1909.08859cs.CLcs.CV

Procedural Reasoning Networks for Understanding Multimodal Procedures

Hacettepe University（哈塞特佩大学）

Mustafa Sercan Amac, Semih Yagcioglu, Aykut Erdem, Erkut Erdem

备注：
Accepted to CoNLL 2019. The project website with code and demo is available at https://hucvl.github.io/prn/
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

英文摘要：

This paper addresses the problem of comprehending procedural commonsense knowledge. This is a challenging task as it requires identifying key entities, keeping track of their state changes, and understanding temporal and causal relations. Contrary to most of the previous work, in this study, we do not rely on strong inductive bias and explore the question of how multimodality can be exploited to provide a complementary semantic signal. Towards this end, we introduce a new entity-aware neural comprehension model augmented with external relational memory units. Our model learns to dynamically update entity states in relation to each other while reading the text instructions. Our experimental analysis on the visual reasoning tasks in the recently proposed RecipeQA dataset reveals that our approach improves the accuracy of the previously reported models by a large margin. Moreover, we find that our model learns effective dynamic representations of entities even though we do not use any supervision at the level of entity states.

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。

↑