A Joint Model for Definition Extraction with Syntactic Connection and Semantic Consistency

Definition Extraction (DE) is one of the well-known topics in Information Extraction that aims to identify terms and thei r corresponding definitions in unstructured texts. This task can be formalized either as a sentence classification task (i.e., containing term-definition pairs or not) or a sequential labeling task (i.e., identifying the boundaries of the terms a nd definitions). The previous works for DE have only focused on one of the two approaches, failing to model the interdependencies between the two tasks. In this work, we propose a novel model for DE that simultaneously performs the two tasks in a single framework to benefit from their interdependencies. Our model features deep learning architectu res to exploit the global structures of the input sentences as we ll as the semantic consistencies between the terms and the definitions, thereby improving the quality of the representat ion vectors for DE. Besides the joint inference between sentenc e classification and sequential labeling, the proposed model is fundamentally different from the prior work for DE in that th e prior work has only employed the local structures of the input sentences (i.e., word-to-word relations), and not yet c on-sidered the semantic consistencies between terms and definitions. In order to implement these novel ideas, our model presents a multi-task learning framework that employs grap h convolutional neural networks and predicts the dependency paths between the terms and the definitions. We also seek to enforce the consistency between the representations of t he terms and definitions both globally (i.e., increasing seman - tic consistency between the representations of the entire s en-tences and the terms/definitions) and locally (i.e., promot ing the similarity between the representations of the terms and the definitions). The extensive experiments on three benchmark datasets demonstrate the effectiveness of our approach.