Continuous Sign Language Recognition Based on Spatial-Temporal Graph Attention Network

Continuous sign language recognition(CSLR)is challenging due to the complexity of video background,hand gesture variability,and temporal modeling difficulties.This work proposes a CSLR method based on a spatialtemporal graph attention network to focus on essential features of video series.The method considers local details of sign language movements by taking the information on joints and bones as inputs and constructing a spatialtemporal graph to reflect inter-frame relevance and physical connections between nodes.The graph-based multihead attention mechanism is utilized with adjacent matrix calculation for better local-feature exploration,and short-term motion correlation modeling is completed via a temporal convolutional network.We adopted BLSTM to learn the long-termdependence and connectionist temporal classification to align the word-level sequences.The proposed method achieves competitive results regarding word error rates(1.59%)on the Chinese Sign Language dataset and the mean Jaccard Index(65.78%)on the ChaLearn LAP Continuous Gesture Dataset.

Infrasound Event Classification Fusion Model Based on Multiscale SE-CNN and BiLSTM

The classification of infrasound events has considerable importance in improving the capability to identify the types of natural disasters.The traditional infrasound classification mainly relies on machine learning algorithms after artificial feature extraction.However,guaranteeing the effectiveness of the extracted features is difficult.The current trend focuses on using a convolution neural network to automatically extract features for classification.This method can be used to extract signal spatial features automatically through a convolution kernel;however,infrasound signals contain not only spatial information but also temporal information when used as a time series.These extracted temporal features are also crucial.If only a convolution neural network is used,then the time dependence of the infrasound sequence will be missed.Using long short-term memory networks can compensate for the missing time-series features but induces spatial feature information loss of the infrasound signal.A multiscale squeeze excitation–convolution neural network–bidirectional long short-term memory network infrasound event classification fusion model is proposed in this study to address these problems.This model automatically extracted temporal and spatial features,adaptively selected features,and also realized the fusion of the two types of features.Experimental results showed that the classification accuracy of the model was more than 98%,thus verifying the effectiveness and superiority of the proposed model.

A multi-attention RNN-based relation linking approach for question answering over knowledge base

Aiming at the relation linking task for question answering over knowledge base,especially the multi relation linking task for complex questions,a relation linking approach based on the multi-attention recurrent neural network(RNN)model is proposed,which works for both simple and complex questions.First,the vector representations of questions are learned by the bidirectional long short-term memory(Bi-LSTM)model at the word and character levels,and named entities in questions are labeled by the conditional random field(CRF)model.Candidate entities are generated based on a dictionary,the disambiguation of candidate entities is realized based on predefined rules,and named entities mentioned in questions are linked to entities in knowledge base.Next,questions are classified into simple or complex questions by the machine learning method.Starting from the identified entities,for simple questions,one-hop relations are collected in the knowledge base as candidate relations;for complex questions,two-hop relations are collected as candidates.Finally,the multi-attention Bi-LSTM model is used to encode questions and candidate relations,compare their similarity,and return the candidate relation with the highest similarity as the result of relation linking.It is worth noting that the Bi-LSTM model with one attentions is adopted for simple questions,and the Bi-LSTM model with two attentions is adopted for complex questions.The experimental results show that,based on the effective entity linking method,the Bi-LSTM model with the attention mechanism improves the relation linking effectiveness of both simple and complex questions,which outperforms the existing relation linking methods based on graph algorithm or linguistics understanding.

Chinese Named Entity Recognition with Character-Level BLSTM and Soft Attention Model

Unlike named entity recognition(NER)for English,the absence of word boundaries reduces the final accuracy for Chinese NER.To avoid accumulated error introduced by word segmentation,a deep model extracting character-level features is carefully built and becomes a basis for a new Chinese NER method,which is proposed in this paper.This method converts the raw text to a character vector sequence,extracts global text features with a bidirectional long short-term memory and extracts local text features with a soft attention model.A linear chain conditional random field is also used to label all the characters with the help of the global and local text features.Experiments based on the Microsoft Research Asia(MSRA)dataset are designed and implemented.Results show that the proposed method has good performance compared to other methods,which proves that the global and local text features extracted have a positive influence on Chinese NER.For more variety in the test domains,a resume dataset from Sina Finance is also used to prove the effectiveness of the proposed method.

基于句法依赖增强图的方面级情感分析

方面级情感分析旨在分析句子中特定方面的情感极性,现有研究侧重于利用图神经网络建模上下文与方面的依赖信息,忽略了对上下文中情感词及其词性的挖掘和利用。为此,提出一种基于句法依赖的增强图(syntactic dependency enhancement graph, SDEG)模型,在原始句法依赖图上引入情感知识和词性信息,增强情感词权重和相关词性单词在上下文中的作用。使用双向长短期记忆网络和卷积神经网络捕捉句子的重点语义信息,通过图卷积神经网络建模句法依赖增强图,通过交互注意力机制生成特定方面的上下文语义和语法表示以进行情感极性分类。在多个公共基准数据集上的实验结果表明,所提模型在性能上有明显提升。

融合TCN和BiLSTM的文本情感分析

为在短文本语义情感分析过程中对词嵌入对情感语义充分表达,挖掘深层次语义信息,提出一种融合TCN和改进BiLSTM的文本情感分析算法。通过混合词嵌入对短文本向量化;将训练后的词向量先输入时序卷积网络,后输入到改进的双向长短时记忆网络中提取情感特征;强制向前注意力机制对提取到的特征进行加权;通过softmax函数进行情感分类输出。通过在新冠疫情评论数据集建模,模型的各项指标均达到92%以上,相较于其它模型性能更优。

融合多层注意力机制与BiLSTM的知识图谱补全算法研究

【目的】针对目前大多数知识图谱补全算法无法兼顾局部与全局特征的问题,本文提出一种对实体间的关系路径进行层级划分,并利用双向长短期记忆网络和多层注意力机制进行特征提取的算法,以对知识图谱进行补全。【方法】首先,结合关系路径上的实体类型和关系得到关系路径序列的向量表示;然后,利用多层注意力机制和双向长短期记忆网络分层级提取序列关键信息;最终通过计算关系路径特征向量与候选关系向量间的相似度得出预测结果。【结果】在NELL-995和FB15k-237数据集上进行链路预测实验,结果表明,该算法与已有基于关系路径的知识图谱补全算法CNN-BiLSTM等相比,MAP值提高了1.8%,Hits@1指标提高了1.4%;在Kinship数据集上,其Hits@3值达到了0.988。【结论】本文通过实验证明了所提出的HAN-BiLSTM算法能有效提取关系路径的整体特征和局部特征,从而提高知识图谱补全效果。

基于MA-BiLSTM的多时间窗航班过站时间估计方法

发生前航延误时,若能精准估计航班链后续航班的机场过站时间,可辅助航空公司适时调整航班计划,有效降低延误波及,同时为机场资源调配提供决策依据.提出了一种基于MA-BiLSTM的多时间窗航班过站时间估计方法.首先对航班过站时间多维度影响因素进行分析选择,然后采用融合双向长短时记忆网络和注意力机制的MA-BiLSTM模型学习航班上、下游过站机场数据的双向时序信息,并获得时间和多维属性的注意力权重,最后根据航班链执行状态设置不同长度的时间窗,采用加权平均方法多时间窗滑动推进动态估计.采用真实航班链数据进行实验,并与常用模型进行对比,结果表明本文方法具有较好的预测准确性.

Speech-driven facial animation with spectral gathering and temporal attention

In this paper,we present an efficient algorithm that generates lip-synchronized facial animation from a given vocal audio clip.By combining spectral-dimensional bidirectional long short-term memory and temporal attention mechanism,we design a light-weight speech encoder that leams useful and robust vocal features from the input audio without resorting to pre-trained speech recognition modules or large training data.To learn subject-independent facial motion,we use deformation gradients as the internal representation,which allows nuanced local motions to be better synthesized than using vertex offsets.Compared with state-of-the-art automatic-speech-recognition-based methods,our model is much smaller but achieves similar robustness and quality most of the time,and noticeably better results in certain challenging cases.