Adding Domain Knowledge to Inductive Learning Methods for Classifying Texts

该研究的重点是通过结合专家领域模型的知识来改进当前的文本分类学习方法。其目标是根据适用于所述案件的因素自动对法律意见书文本进行分类。因素——倾向于加强或削弱案件中潜在法律主张的刻板事实模式，以及它们与法律问题的关系——是一种在法律论证中有用的专业领域知识。该程序将法律意见的原始文本作为输入，并将适用因素分配为输出。该程序的训练实例是从法律意见语料库中提取的，这些法律意见的文本描述是根据因素手工表示的。这个问题很难，因为意见的语言很复杂；一项意见讨论了各种因素，这一事实并不一定意味着这些因素实际上适用于该案件。本研究从现有的几种归纳和统计学习算法入手，评估了加入四种不同类型的领域知识是否能提高算法的性能：(1)关于因素和与之相关的法律问题的领域知识；（二）法律意见书结构的一般情况；（三）意见书所引用法律的有关情况；（四）因素已知的意见所引案件的有关情况。这项工作还探讨了(a)如何结合归纳和分析技术来处理少量的训练实例，以及(b)如何最好地结合成功的归纳、统计和基于知识的方法。使用领域知识来指导自动文本分类，集成了信息检索、机器学习和人工智能知识表示技术，将有助于扩展基于案例的推理系统，并缓解在越来越大的在线数据库中评估文本相关性的问题。

The research focuses on improving current methods for learning to classify texts by incorporating knowledge from an expert domain model. The goal is automatically to classify the texts of legal opinions in terms of the factors that apply to the cases described. Factors -- stereotypical fact patterns tending to strengthen or weaken the underlying legal claims in a case, and their relations to legal issues -- are a kind of expert domain knowledge useful in legal argumentation. The program takes as inputs the raw texts of legal opinions and assigns as outputs the applicable factors. The program's training instances are drawn from a corpus of legal opinions whose textual descriptions of cases have been represented manually in terms of factors. The problem is hard because the language of the opinions is complex; the mere fact that an opinion discusses factors does not necessarily imply that those factors actually apply to the case. Starting with several existing inductive and statistical learning algorithms, this research assesses whether adding four different kinds of domain knowledge improves the algorithms' performance: (1) domain knowledge about factors and the legal issues to which they relate; (2) general information about the structure of legal opinions; (3) information about the statutes quoted in an opinion; (4) information about those cases cited in an opinion whose factors are known. The work also explores (a) how to combine inductive and analytical techniques to deal with small numbers of training instances and (b) how best to combine successful inductive, statistical, and knowledge-based methods. Using domain knowledge to guide automatic text classification integrates information retrieval, machine learning and AI knowledge-representation techniques, will help scale up case-based reasoning systems, and alleviate the problem of assessing the relevance of texts in increasingly large on-line databases.