摘要：Existing literature demonstrates that verbs are pivotal in legal information extraction tasksdue to their semantic and argumentative properties. However, granting computers the ability tointerpret the meaning of a verb and its semantic properties in relation to a given context can beconsidered as a challenging task, mainly due to the polysemic and domain specific behaviours ofverbs. Therefore, developing mechanisms to identify behaviors of verbs and evaluate how artificialmodels detect the domain specific and polysemic behaviours of verbs can be considered as tasks withsignificant importance. In this regard, a comprehensive dataset that can be used as an evaluationresource, as well as a training data set, can be considered as a major requirement. In this paper,we introduce LeCoVe, which is a verb similarity dataset intended towards facilitating the process ofidentifying verbs with similar meanings in a legal domain specific context. Using the dataset, weevaluated both domain specific and domain generic embedding models, which were developed usingstate-of-the-art word representation and language modelling techniques. As a part of the experimentscarried out using the announced dataset, Sense2Vec and BERT models were trained using a corpusof legal opinion texts in order to capture domain specific behaviours. In addition to LeCoVe, wedemonstrate that a neural network model, which was developed by combining semantic, syntactic,and contextual features that can be obtained from the outputs of embedding models, can performcomparatively well, even in a low resource scenario.
关键词：information semantics;word embeddings;deep learning;natural language processing
