Knowledge representation is one of the critical problems in knowledge engineering and artificial intelligence, while knowledge embedding as a knowledge representation methodology indicates entities and relations in knowledge graph as low-dimensional, continuous vectors. In this way, knowledge graph is compatible with machine learning models. Major knowledge embedding methods employ geometric translation to design score function, which is weak-semantic for natural language processing. To overcome this disadvantage, in this paper, we propose our model based on multi-view clustering framework, which could generate semantic representations of knowledge elements (i.e. entities/relations). With our semantic model, we also present an empowered solution to entity retrieval with entity description. Extensive experiments show that our model achieves substantial improvements against baselines on the task of knowledge graph completion, triple classification, entity classification and entity retrieval.

Sign language translation (SLT) is an important application to bridge the communication gap between deaf and hearing people. In recent years, the research on the SLT based on neural translation frameworks has attracted wide attention. Despite the progress, current SLT research is still in the initial stage. In fact, current systems perform poorly in processing long sign sentences, which often involve long-distance dependencies and require large resource consumption. To tackle this problem, we propose two explainable adaptations to the traditional neural SLT models using optimized tokenization-related modules. First, we introduce a frame stream density compression (FSDC) algorithm for detecting and reducing the redundant similar frames, which effectively shortens the long sign sentences without losing information. Then, we replace the traditional encoder in a neural machine translation (NMT) module with an improved architecture, which incorporates a temporal convolution (T-Conv) unit and a dynamic hierarchical bidirectional GRU (DH-BiGRU) unit sequentially. The improved component takes the temporal tokenization information into consideration to extract deeper information with reasonable resource consumption. Our experiments on the RWTH-PHOENIX-Weather 2014T dataset show that the proposed model outperforms the state-of-the-art baseline up to about 1.5+ BLEU-4 score gains.

Sign language translation (SLT) aims to convert continuous sign language videos into textual sentences. As a typical multi-modal task, there exists an inherent modality gap between sign language videos and spoken language text, which makes the cross-modal alignment between visual and textual modalities crucial. However, previous studies tend to rely on an intermediate sign gloss representation to help alleviate the cross-modal problem thereby neglecting the alignment across modalities that may lead to compromised results. To address this issue, we propose a novel framework based on Conditional Variational autoencoder for SLT (CV-SLT) that facilitates direct and sufficient cross-modal alignment between sign language videos and spoken language text. Specifically, our CV-SLT consists of two paths with two Kullback-Leibler (KL) divergences to regularize the outputs of the encoder and decoder, respectively. In the prior path, the model solely relies on visual information to predict the target text; whereas in the posterior path, it simultaneously encodes visual information and textual knowledge to reconstruct the target text. The first KL divergence optimizes the conditional variational autoencoder and regularizes the encoder outputs, while the second KL divergence performs a self-distillation from the posterior path to the prior path, ensuring the consistency of decoder outputs.We further enhance the integration of textual information to the posterior path by employing a shared Attention Residual Gaussian Distribution (ARGD), which considers the textual information in the posterior path as a residual component relative to the prior path. Extensive experiments conducted on public datasets demonstrate the effectiveness of our framework, achieving new state-of-the-art results while significantly alleviating the cross-modal representation discrepancy. The code and models are available at https://github.com/rzhao-zhsq/CV-SLT.

The differential evolution (DE) algorithm is a heuristic global optimization technique based on population which is easy to understand, simple to implement, reliable, and fast. The evolutionary parameters directly influence the performance of differential evolution algorithm. The adjustment of control parameters is a global behavior and has no general research theory to control the parameters in the evolution process at present. In this paper, we propose an adaptive parameter adjustment method which can dynamically adjust control parameters according to the evolution stage. The experiments on high dimensional function optimization showed that the improved algorithm has more powerful global exploration ability and faster convergence speed.

Artificial fish swarm algorithm (AFSA) is a population based optimization technique inspired by social behavior of fishes. In past several years, AFSA has been successfully applied in many research and application areas. The behavior of fishes has a crucial impact on the performance of AFSA, such as global exploration ability and convergence speed. How to construct and select behaviors of fishes are an important task. To solve these problems, an improved artificial fish swarm algorithm based on log-linear model is proposed and implemented in this paper. There are three main works. Firstly, we proposed a new behavior selection algorithm based on log-linear model which can enhance decision making ability of behavior selection. Secondly, adaptive movement behavior based on adaptive weight is presented, which can dynamically adjust according to the diversity of fishes. Finally, some new behaviors are defined and introduced into artificial fish swarm algorithm at the first time to improve global optimization capability. The experiments on high dimensional function optimization showed that the improved algorithm has more powerful global exploration ability and reasonable convergence speed compared with the standard artificial fish swarm algorithm.