基于深度注意神经网络的大规模学术论文主题类别分类
Large Scale Subject Category Classification of Scholarly Papers with Deep Attentive Neural Networks
摘要：
学术论文的主题类别通常是指论文所属的知识领域，例如计算机科学或物理学。利用学科分类信息可以构建数字图书馆搜索引擎的分面搜索。这可以极大地帮助用户缩小相关文档的搜索空间。不幸的是，许多学术论文的元数据中并没有这样的信息。解决这一问题的现有方法通常集中在无监督学习上，而无监督学习往往依赖于引文网络。然而，引用当前论文的完整列表可能不容易获得。特别是，引用很少或没有引用的新论文不能使用这种方法进行分类。在这里，我们提出了一个深度关注的神经网络（DANN），分类学术论文只使用他们的摘要。该网络使用来自Web of Science（WoS）的900万篇摘要进行训练。我们还使用了WoS模式，涵盖了104个主题类别。该网络由两个双向递归神经网络和一个注意层组成。我们通过改变架构和文本表示来将我们的模型与基线进行比较。我们最好的模型实现了0.76的微观F1测量值，单个主题类别的F1范围为0.50-0.95。结果表明，重新训练词嵌入模型的重要性，以最大限度地提高词汇重叠和注意力机制的有效性。词向量与TFIDF的组合优于字符和句子级别的嵌入模型。我们讨论了不平衡的样本和重叠的类别，并提出了可能的缓解策略。我们还通过对100万篇学术论文的随机样本进行分类来确定CiteSeerX中的主题类别分布。
英文摘要：
Subject categories of scholarly papers generally refer to the knowledge domain(s) to which the papers belong, examples being computer science or physics. Subject category information can be used for building faceted search for digital library search engines. This can significantly assist users in narrowing down their search space of relevant documents. Unfortunately, many academic papers do not have such information as part of their metadata. Existing methods for solving this task usually focus on unsupervised learning that often relies on citation networks. However, a complete list of papers citing the current paper may not be readily available. In particular, new papers that have few or no citations cannot be classified using such methods. Here, we propose a deep attentive neural network (DANN) that classifies scholarly papers using only their abstracts. The network is trained using 9 million abstracts from Web of Science (WoS). We also use the WoS schema that covers 104 subject categories. The proposed network consists of two bi-directional recurrent neural networks followed by an attention layer. We compare our model against baselines by varying the architecture and text representation. Our best model achieves micro-F1 measure of 0.76 with F1 of individual subject categories ranging from 0.50-0.95. The results showed the importance of retraining word embedding models to maximize the vocabulary overlap and the effectiveness of the attention mechanism. The combination of word vectors with TFIDF outperforms character and sentence level embedding models. We discuss imbalanced samples and overlapping categories and suggest possible strategies for mitigation. We also determine the subject category distribution in CiteSeerX by classifying a random sample of one million academic papers.
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。
