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 their 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 and definitions). The previous works for DE have only focused on one of the two approaches, failing to model the inter-dependencies 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 inter-dependencies. Our model features deep learning architectures to exploit the global structures of the input sentences as well as the semantic consistencies between the terms and the definitions, thereby improving the quality of the representation vectors for DE. Besides the joint inference between sentence classification and sequential labeling, the proposed model is fundamentally different from the prior work for DE in that the prior work has only employed the local structures of the input sentences (i.e., word-to-word relations), and not yet considered the semantic consistencies between terms and definitions. In order to implement these novel ideas, our model presents a multi-task learning framework that employs graph 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 the terms and definitions both globally (i.e., increasing semantic consistency between the representations of the entire sentences and the terms/definitions) and locally (i.e., promoting the similarity between the representations of the terms and the definitions). The extensive experiments on three benchmark datasets demonstrate the effectiveness of our approach.1

Sequential Super-Resolution Imaging using DNA Strand Displacement

Sequential labeling and imaging in fluorescence microscopy allows the imaging of multiple structures in the same cell using a single fluorophore species. In super-resolution applications, the optimal dye suited to the method can be chosen, the optical setup can be simpler and there are no chromatic aberrations between images of different structures. We describe a method based on DNA strand displacement that can be used to quickly and easily perform the labeling and removal of the fluorophores during each sequence. Site-specific tags are conjugated with unique and orthogonal single stranded DNA. Labeling for a particular structure is achieved by hybridization of antibody-bound DNA with a complimentary dye-labeled strand. After imaging, the dye is removed using toehold-mediated strand displacement, in which an invader strand competes off the dye-labeled strand than can be subsequently washed away. Labeling and removal of each DNA-species requires only a few minutes. We demonstrate the concept using sequential dSTORM super-resolution for multiplex imaging of subcellular structures.