The Klarna Product Page Dataset: Web Element Nomination with Graph Neural Networks and Large Language Models

arXiv:2111.02168v4 Announce Type: replace
Abstract: Web automation holds the potential to revolutionize how users interact with the digital world, offering unparalleled assistance and simplifying tasks via sophisticated computational methods. Central to this evolution is the web element nomination task, which entails identifying unique elements on webpages. Unfortunately, the development of algorithmic designs for web automation is hampered by the scarcity of comprehensive and realistic datasets that reflect the complexity faced by real-world applications on the Web. To address this, we …

abstract arxiv automation computational cs.cl cs.cv cs.hc cs.ir cs.lg dataset digital digital world element evolution graph graph neural networks klarna language language models large language large language models networks neural networks page product simplifying tasks type via web world