一种用于自定义文本分类的分类元数据表示方法
Categorical Metadata Representation for Customized Text Classification
摘要：
使用智能工程的基于神经的模型，文本分类的性能得到了极大的改善，特别是那些注入分类元数据作为附加信息的模型，例如，使用用户/产品信息进行情感分类。这些信息已被用于修改模型的部分（例如，词嵌入、注意力机制），使得可以根据元数据定制结果。我们观察到，目前的分类元数据的表示方法，这是为人类消费而设计的，并不像流行的分类方法中所声称的那样有效，甚至在句子编码器的最后一层中通过简单的分类特征的级联来表现。我们推测，分类特征更难表示为机器使用，因为可用的上下文只能间接描述类别，甚至这样的上下文往往是稀缺的（尾类别）。为此，我们建议使用基向量来有效地将分类元数据整合到基于神经的模型的各个部分。这额外地显著减少了参数的数量，特别是当分类特征的数量很大时。在不同属性的数据集上进行了大量的实验，结果表明，通过我们的方法，我们可以更有效地表示分类元数据，以定制模型的部分，包括未开发的部分，并大大提高模型的性能。
英文摘要：
The performance of text classification has improved tremendously using intelligently engineered neural-based models, especially those injecting categorical metadata as additional information, e.g., using user/product information for sentiment classification. These information have been used to modify parts of the model (e.g., word embeddings, attention mechanisms) such that results can be customized according to the metadata. We observe that current representation methods for categorical metadata, which are devised for human consumption, are not as effective as claimed in popular classification methods, outperformed even by simple concatenation of categorical features in the final layer of the sentence encoder. We conjecture that categorical features are harder to represent for machine use, as available context only indirectly describes the category, and even such context is often scarce (for tail category). To this end, we propose to use basis vectors to effectively incorporate categorical metadata on various parts of a neural-based model. This additionally decreases the number of parameters dramatically, especially when the number of categorical features is large. Extensive experiments on various datasets with different properties are performed and show that through our method, we can represent categorical metadata more effectively to customize parts of the model, including unexplored ones, and increase the performance of the model greatly.
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。
