(未能)用深度学习理解拉丁诗歌风格
(Not) Understanding Latin Poetic Style with Deep Learning
AI总结:
研究用LSTM与CNN分析含声音、格律特征的拉丁诗歌以识别作者风格,发现分类准确但注意力推理难解释,并指出CNN、可训练嵌入及防过拟合技术更优。
摘要:
本文总结了一些大多未获成功的尝试,旨在通过考察各种神经网络(LSTM和CNN)的注意力来理解作者风格;这些网络在一个古典拉丁诗语料库上训练,语料经过编码以包含声音和格律特征。研究表明,经过精心配置的神经网络是极其强大的作者身份分类器,因此人们希望它们或许能由此向“传统”读者揭示作者在风格上如何不同。遗憾的是,迄今为止,它们的推理过程仍难以理解。尽管总体目标尚未实现,但本工作报告了一些有用发现,涉及对诗歌进行编码和嵌入的有效方法、不同神经网络家族的相对优势与弱点,以及在该领域设计和检查NN模型时有用(以及不那么有用)的技术。本文认为,对于诗歌而言,CNN是比LSTM更好的选择——它们训练更快,准确率相当,并且(可能)提供更好的可解释性。基于大量实验,文章还认为,简单、可训练的嵌入比面向特定领域的方案更有效,并强调了使用dropout和batch normalization等技术降低过拟合的重要性。
英文摘要:
This article summarizes some mostly unsuccessful attempts to understand authorial style by examining the attention of various neural networks (LSTMs and CNNs) trained on a corpus of classical Latin verse that has been encoded to include sonic and metrical features. Carefully configured neural networks are shown to be extremely strong authorship classifiers, so it is hoped that they might therefore teach `traditional' readers something about how the authors differ in style. Sadly their reasoning is, so far, inscrutable. While the overall goal has not yet been reached, this work reports some useful findings in terms of effective ways to encode and embed verse, the relative strengths and weaknesses of the neural network families, and useful (and not so useful) techniques for designing and inspecting NN models in this domain. This article suggests that, for poetry, CNNs are better choices than LSTMs -- they train more quickly, have equivalent accuracy, and (potentially) offer better interpretability. Based on a great deal of experimentation, it also suggests that simple, trainable embeddings are more effective than domain-specific schemes, and stresses the importance of techniques to reduce overfitting, like dropout and batch normalization.
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。