While natural language understanding of long-form documents is still an open challenge, such documents often contain structural information that can inform the design of models for encoding them. Movie scripts are an example of such richly structured text - scripts are segmented into scenes, which are further decomposed into dialogue and descriptive components. In this work, we propose a neural architecture for encoding this structure, which performs robustly on a pair of multi-label tag classification datasets, without the need for handcrafted features. We add a layer of insight by augmenting an unsupervised "interpretability" module to the encoder, allowing for the extraction and visualization of narrative trajectories. Though this work specifically tackles screenplays, we discuss how the underlying approach can be generalized to a range of structured documents.
LinguaLens: Towards Interpreting Linguistic Mechanisms of Large Language Models via Sparse Auto-Encoder
DCST, BNRist（DCST、BNRist；KIRC、人工智能研究院、清华大学，中国）；KIRC, Institute for Artificial Intelligence, Tsinghua University, China（中文语言文学系、北京大学，中国）；Department of Chinese Language and Literature, Peking University, China
Department of Computer & Information Science & Engineering, University of Florida（佛罗里达大学计算机与信息科学与工程系）；School of Computer Science, University of Oklahoma（俄克拉荷马大学计算机科学学院）；Department of Electrical Engineering and Computer Science, United States Military Academy（美国军事学院电子工程与计算机科学系）
Chart-to-Text: Generating Natural Language Descriptions for Charts by Adapting the Transformer Model
York University（约克大学）
信息可视化（如条形图和折线图）在探索数据和传达见解方面非常受欢迎。对某些人来说，解释和理解这种可视化可能具有挑战性，例如那些视力受损或视觉素养低的人。在这项工作中，我们引入了一个新的数据集，并提出了一个神经模型自动生成图表的自然语言摘要。生成的摘要提供了对图表的解释，并传达了在该图表中发现的关键见解。我们的神经模型是通过扩展数据到文本生成任务的最先进模型开发的，该模型利用了基于transformer的编码器-解码器架构。我们发现，我们的方法在内容选择指标上远远优于基础模型（55.42% vs. 8.49%），并生成了更多信息，简洁和连贯的摘要。
