A Knowledge-Enriched and Span-Based Network for Joint Entity and Relation Extraction

The joint extraction of entities and their relations from certain texts plays a significant role in most natural language processes.For entity and relation extraction in a specific domain,we propose a hybrid neural framework consisting of two parts:a span-based model and a graph-based model.The span-based model can tackle overlapping problems compared with BILOU methods,whereas the graph-based model treats relation prediction as graph classification.Our main contribution is to incorporate external lexical and syntactic knowledge of a specific domain,such as domain dictionaries and dependency structures from texts,into end-to-end neural models.We conducted extensive experiments on a Chinese military entity and relation extraction corpus.The results show that the proposed framework outperforms the baselines with better performance in terms of entity and relation prediction.The proposed method provides insight into problems with the joint extraction of entities and their relations.

Combing Type-Aware Attention and Graph Convolutional Networks for Event Detection

Event detection(ED)is aimed at detecting event occurrences and categorizing them.This task has been previously solved via recognition and classification of event triggers(ETs),which are defined as the phrase or word most clearly expressing event occurrence.Thus,current approaches require both annotated triggers as well as event types in training data.Nevertheless,triggers are non-essential in ED,and it is time-wasting for annotators to identify the“most clearly”word from a sentence,particularly in longer sentences.To decrease manual effort,we evaluate event detectionwithout triggers.We propose a novel framework that combines Type-aware Attention and Graph Convolutional Networks(TA-GCN)for event detection.Specifically,the task is identified as a multi-label classification problem.We first encode the input sentence using a novel type-aware neural network with attention mechanisms.Then,a Graph Convolutional Networks(GCN)-based multilabel classification model is exploited for event detection.Experimental results demonstrate the effectiveness.

Overview of Bio-Oil from Sewage Sludge by Direct Thermochemical Liquefaction Technology

Sewage sludge is an unavoidable secondary pollution produced in the process of sewage treatment. At present traditional methods of treating sludge (e.g. landfill, incineration or land application) have some disadvantages and shortages. Direct thermochemical liquefaction of sludge is a new treatment method, which has the advantage of both treatment and energy recovery. Research progress and application prospect of sludge liquefaction technology are widely reported, typical liquefaction process with bio-oil production and its main influencing factors are introduced. Besides, the devel- opment of this process is illustrated, and resource and energy recovery of this technology are pointed out to be the ten- dency of sludge treatment in the future.

A Cumulative Prospect Theory Based Counterterrorism Resource Allocation Method under Interval Values

Strategic resource allocation into decision-making model plays a valuable role for the defender in mitigating damage and improving efficiency in military environments.In this paper,we develop a defensive resource allocation model based on cumulative prospect theory (CPT),which considers terrorists' psychological factors of decision-making in reality.More specifically,we extend existing models in the presence of multiple attributes and terrorists' deviations from rationality using a multi-attribute cumulative prospect theory.In addition,interval values are used to cope with uncertainties regarding gain and loss.Comparative studies are also carried out to demonstrate the differences among minmax,Nash equilibrium (NE),and traditional probability risk analysis (PRA) strategies.Results show that the defender's optimal defensive resource allocation will change along with terrorists' behaviors and the proposed model makes more sense compared with other traditional resource allocation strategies.