We consider a novel question answering (QA) task where the machine needs to read from large streaming data (long documents or videos) without knowing when the questions will be given, which is difficult to solve with existing QA methods due to their lack of scalability. To tackle this problem, we propose a novel end-to-end deep network model for reading comprehension, which we refer to as Episodic Memory Reader (EMR) that sequentially reads the input contexts into an external memory, while replacing memories that are less important for answering unseen questions. Specifically, we train an RL agent to replace a memory entry when the memory is full, in order to maximize its QA accuracy at a future timepoint, while encoding the external memory using either the GRU or the Transformer architecture to learn representations that considers relative importance between the memory entries. We validate our model on a synthetic dataset (bAbI) as well as real-world large-scale textual QA (TriviaQA) and video QA (TVQA) datasets, on which it achieves significant improvements over rulebased memory scheduling policies or an RLbased baseline that independently learns the query-specific importance of each memory.

Polystyrene (PS) microspheres selectively coated with multiwalled carbon nanotubes (MWCNTs) were prepared by in situ suspension polymerization. The styrene monomer was polymerized in an aqueous matrix with poly(vinyl pyrrolidone) (PVP), MWCNTs and 2,2-azobisisobutyronitrile. PVP was used as both as an agent for dispersing the MWCNTs using a wrapping strategy in an aqueous system and as a steric stabilizer for styrene droplets. Therefore, MWCNTs wrapped with PVP were dispersed on the surface of PS microspheres. Scanning and transmission electron microscopy confirmed that the MWCNTs were located only on the surface of the S-PS/MWCNT microspheres. The electrical conductivity of the MWCNT-network on the surface of the PS microspheres was analyzed by electrical resistance measurements. Overall, PS/MWCNT microspheres can be used to produce highly concentrated MWCNT-dispersed PS films by hot compression.

No abstract