用上下文嵌入预测演示幻灯片重点的AAAI-CAD21共享任务中思科的表现

Jan, 2021

用上下文嵌入预测演示幻灯片重点的AAAI-CAD21共享任务中思科的表现

Cisco at AAAI-CAD21 shared task: Predicting Emphasis in Presentation Slides using Contextualised Embeddings

Sreyan Ghosh, Sonal Kumar, Harsh Jalan, Hemant Yadav, Rajiv Ratn Shah

TL;DR本文提出了两种方法（BiLSTM-ELMo和基于RoBERTa和XLNet的transformers）来预测幻灯片中每个单词的强调程度，并在评估排行榜上获得了0.518分，位列第3名，在后评估排行榜上获得了0.543分，位列第1名。

Abstract

This paper describes our proposed system for the aaai-cad21 shared task: Predicting Emphasis in Presentation Slides. In this specific task, given the contents of a slide we are asked to predict the degree of emphasis to be laid on each word in the slide. We propose 2 approaches to this