法律文书命名实体识别是智慧司法的关键任务。现有的序列标注模型仅关注字符信息,导致在法律文书命名实体识别任务中无法获得语义和词语的上下文信息,且无法对实体的边界进行限制。因此,该文提出了一个融合外部信息并对边界限制的司法...法律文书命名实体识别是智慧司法的关键任务。现有的序列标注模型仅关注字符信息,导致在法律文书命名实体识别任务中无法获得语义和词语的上下文信息,且无法对实体的边界进行限制。因此,该文提出了一个融合外部信息并对边界限制的司法命名实体识别模型(semantic and boundary enhance named entity recognition,SBENER)。该模型收集了40万条盗窃罪法律文书,首先,预训练模型,将获得的司法盗窃罪词向量作为输入模型的外部信息;其次,设计Adapter,将司法盗窃罪的信息融入字符序列以增强语义特征;最后,使用边界指针网络对实体边界进行限制,解决了序列标注模型丢失词语信息及缺少边界限制的问题。该模型在CAILIE 1.0数据集和LegalCorpus数据集上进行实验,结果表明,SBENER模型在2个数据集上的F_1值(F_1-score)分别达88.70%和87.67%,比其他基线模型取得了更好的效果。SBENER模型能够提升司法领域命名实体识别的效果。展开更多
With the development of economic globalization,legal English has been developing very fast as one kind of ESP.Compared with general English,legal English is a special language style,which is characterized by stability...With the development of economic globalization,legal English has been developing very fast as one kind of ESP.Compared with general English,legal English is a special language style,which is characterized by stability,oddities and exactness.The language used in legal document belongs to a special kind of legal English,and has its own language characters like other social dialects.The paper analyses the features of the language of legal document from lexical and syntactic level.展开更多
文摘法律文书命名实体识别是智慧司法的关键任务。现有的序列标注模型仅关注字符信息,导致在法律文书命名实体识别任务中无法获得语义和词语的上下文信息,且无法对实体的边界进行限制。因此,该文提出了一个融合外部信息并对边界限制的司法命名实体识别模型(semantic and boundary enhance named entity recognition,SBENER)。该模型收集了40万条盗窃罪法律文书,首先,预训练模型,将获得的司法盗窃罪词向量作为输入模型的外部信息;其次,设计Adapter,将司法盗窃罪的信息融入字符序列以增强语义特征;最后,使用边界指针网络对实体边界进行限制,解决了序列标注模型丢失词语信息及缺少边界限制的问题。该模型在CAILIE 1.0数据集和LegalCorpus数据集上进行实验,结果表明,SBENER模型在2个数据集上的F_1值(F_1-score)分别达88.70%和87.67%,比其他基线模型取得了更好的效果。SBENER模型能够提升司法领域命名实体识别的效果。
文摘With the development of economic globalization,legal English has been developing very fast as one kind of ESP.Compared with general English,legal English is a special language style,which is characterized by stability,oddities and exactness.The language used in legal document belongs to a special kind of legal English,and has its own language characters like other social dialects.The paper analyses the features of the language of legal document from lexical and syntactic level.
