The main purpose of the joint entity and relation extraction is to extract entities from unstructured texts and extract the relation between labeled entities at the same time. At present, most existing joint entity and relation extraction networks ignore the utilization of explicit semantic information and explore implicit semantic information insufficiently. In this paper, we propose Joint Entity and Relation Extraction Network with Enhanced Explicit and Implicit Semantic Information (EINET). First, on the premise of using the pre-trained model, we introduce explicit semantics from Semantic Role Labeling (SRL), which contains rich semantic features about the entity types and relation of entities. Then, to enhance the implicit semantic information and extract richer features of the entity and local context, we adopt different Bi-directional Long Short-Term Memory (Bi-LSTM) networks to encode entities and local contexts, respectively. In addition, we propose to integrate global semantic information and local context length representation in relation extraction to further improve the model performance. Our model achieves competitive results on three publicly available datasets. Compared with the baseline model on Conll04, EINET obtains improvements by 2.37% in F1 for named entity recognition and 3.43% in F1 for relation extraction.
We propose a heterogeneous, mid-level feature based method for recognizing natural scene categories. The proposed feature introduces spatial information am
Aim: A hallmark of classical conditioning is that conditioned stimulus (CS) must be tightly coupled with unconditioned stimulus (US), often requiring temporal overlap between the two, or a short gap of several seconds. In this study, we investigate the temporal requirements for fear conditioning association between a strong artificial CS, high-frequency optogenetic activation of inputs into the lateral amygdala of rats, and a foot-shock to the animal with delays up to many minutes. Methods: AAV-oChIEF-tdTomato viruses were injected into the auditory cortex and the medial geniculate nucleus of rats. An optical fiber was implanted just above the lateral amygdala of the animal. Optogenetic high-frequency stimuli (oHFS; containing five 1-s trains of 100 Hz laser pulses) were delivered to the lateral amygdala, before or after (with varying intervals) a foot-shock that elicits fear responses in the animal. Pre-trained lever-press behavior was used to assess the degree of fear recall by optogenetic test stimuli (OTS; 10 Hz for 2 min) 24 h after the association experiment. Results: In contrast to the tight temporal requirement for classical conditioning with paired optogenetic moderate-frequency stimuli (oMFS; 10 Hz for 20 s) and foot-shock, oHFS followed by foot-shock with a 5-min or even 1-h (but not 3-h) interval could successfully establish an association to be recalled by OTS the next day. Meanwhile, foot-shock followed by oHFS with a 5-min (but not 1-h) interval could also establish the conditioning. Thus, distant association may be formed between temporally distant stimuli when the CS is strong.
Estimating 3D human poses from 2D poses is a challenging problem due to joints self-occlusion, weak generalization, and inherent ambiguity of recovering depth. Actually, there exists spatial structure dependence on human body key points which can be used to alleviate the problem of joints self-occlusion. Therefore, we represent human pose as a directed graph and propose a network implemented with graph convolution to predict 3D poses from the given 2D poses. In the digraph, we determine the connection weight of each edge according to the error distribution of joints estimation. This makes our model robust to noise. By optimizing coarse 3D estimation and adversarial learning, our algorithm can successfully improve the accuracy of estimation and relieve the ambiguity of mapping. Through testing on Human 3.6M and MPI-INF-3DHP datasets, we achieve excellent quantitative performance. More importantly, our algorithm also has a superior generalization to outdoor dataset MPII by the pre-training process.