Most existing joint neural models for Information Extraction (IE) use local task-specific classifiers to predict labels for individual instances (e.g., trigger, relation) regardless of their interactions. For example, a VICTIM of a DIE event is likely to be a VICTIM of an AT-TACK event in the same sentence. In order to capture such cross-subtask and cross-instance inter-dependencies, we propose a joint neural framework, ONEIE, that aims to extract the globally optimal IE result as a graph from an input sentence. ONEIE performs end-to-end IE in four stages: (1) Encoding a given sentence as contextualized word representations;(2) Identifying entity mentions and event triggers as nodes; (3) Computing label scores for all nodes and their pairwise links using local classifiers; (4) Searching for the globally optimal graph with a beam decoder. At the decoding stage, we incorporate global features to capture the cross-subtask and cross-instance interactions. Experiments show that adding global features improves the performance of our model and achieves new state-of-the-art on all subtasks. As ONEIE does not use any language-specific feature, we prove it can be easily applied to new languages or trained in a multilingual manner. Our code and models for English, Spanish and Chinese are publicly available for research purpose 1 . PER Erdogan PER Abdullah Gul End-Position resigned Elect won person personExample: Prime Minister Abdullah Gul resigned earlier Tuesday to make way for Erdogan, who won a parliamentary seat in by-elections Sunday.

Polylactide (PLA) was melt blended with a biodegradable hyperbranched poly(ester amide) (HBP) to enhance its flexibility and toughness without sacrificing comprehensive performance. The advantage of using HBP was due to its unique spherical shape, low melt viscosity, and abundant functional end groups together with its easy access. Rheological measurement showed that blending PLA with as little as 2.5% HBP resulted in a 40% reduction of melt viscosity. The glass transition temperature (T g) of PLA in the blends decreased slightly with the increase of HBP content, indicating partial miscibility which resulted from intermolecular interactions via H-bonding. The H-bonding involving CO of PLA with OH and NH of HBP was evidenced by FTIR analysis for the first time. The HBP component, as a heterogeneous nucleating agent, accelerated the crystallization rate of PLA. Remarkably, with the increase of HBP content, the elongation at break of PLA blends dramatically increased without severe loss in tensile strength, even the tensile strength increased within 10% content of HBP. The stress−strain curves and the SEM photos of impact-fractured surface showed the material changed from brittle to ductile failure with the addition of HBP. Reasonable interfacial adhesion via H-bonding and finely dispersed particulate structure of HBP in PLA were proposed to be responsible for the improved mechanical properties.

No abstract