Semantic role labeling based on conditional random fields

Due to the fact that semantic role labeling （SRL） is very necessary for deep natural language processing, a method based on conditional random fields （CRFs） is proposed for the SRL task. This method takes shallow syntactic parsing as the foundation, phrases or named entities as the labeled units, and the CRFs model is trained to label the predicates＇ semantic roles in a sentence. The key of the method is parameter estimation and feature selection for the CRFs model. The L-BFGS algorithm was employed for parameter estimation, and three category features： features based on sentence constituents, features based on predicate, and predicate-constituent features as a set of features for the model were selected. Evaluation on the datasets of CoNLL-2005 SRL shared task shows that the method can obtain better performance than the maximum entropy model, and can achieve 80. 43 % precision and 63. 55 % recall for semantic role labeling.

TONE MODELING BASED ON HIDDEN CONDITIONAL RANDOM FIELDS AND DISCRIMINATIVE MODEL WEIGHT TRAINING

The use of hidden conditional random fields （HCRFs） for tone modeling is explored. The tone recognition performance is improved using HCRFs by taking advantage of intra-syllable dynamic, inter-syllable dynamic and duration features. When the tone model is integrated into continuous speech recognition, the discriminative model weight training （DMWT） is proposed. Acoustic and tone scores are scaled by model weights discriminatively trained by the minimum phone error （MPE） criterion. Two schemes of weight training are evaluated and a smoothing technique is used to make training robust to overtraining problem. Experiments show that the accuracies of tone recognition and large vocabulary continuous speech recognition （LVCSR） can be improved by the HCRFs based tone model. Compared with the global weight scheme, continuous speech recognition can be improved by the discriminative trained weight combinations.

Power entity recognition based on bidirectional long short-term memory and conditional random fields

With the application of artificial intelligence technology in the power industry,the knowledge graph is expected to play a key role in power grid dispatch processes,intelligent maintenance,and customer service response provision.Knowledge graphs are usually constructed based on entity recognition.Specifically,based on the mining of entity attributes and relationships,domain knowledge graphs can be constructed through knowledge fusion.In this work,the entities and characteristics of power entity recognition are analyzed,the mechanism of entity recognition is clarified,and entity recognition techniques are analyzed in the context of the power domain.Power entity recognition based on the conditional random fields (CRF) and bidirectional long short-term memory (BLSTM) models is investigated,and the two methods are comparatively analyzed.The results indicated that the CRF model,with an accuracy of 83%,can better identify the power entities compared to the BLSTM.The CRF approach can thus be applied to the entity extraction for knowledge graph construction in the power field.

A CONDITIONAL RANDOM FIELDS APPROACH TO BIOMEDICAL NAMED ENTITY RECOGNITION

Named entity recognition is a fundamental task in biomedical data mining. In this letter, a named entity recognition system based on CRFs （Conditional Random Fields） for biomedical texts is presented. The system makes extensive use of a diverse set of features, including local features, full text features and external resource features. All features incorporated in this system are described in detail, and the impacts of different feature sets on the performance of the system are evaluated. In order to improve the performance of system, post-processing modules are exploited to deal with the abbreviation phenomena, cascaded named entity and boundary errors identification. Evaluation on this system proved that the feature selection has important impact on the system performance, and the post-processing explored has an important contribution on system performance to achieve better resuits.

Adaptive foreground and shadow segmentation using hidden conditional random fields

Video object segmentation is important for video surveillance, object tracking, video object recognition and video editing. An adaptive video segmentation algorithm based on hidden conditional random fields (HCRFs) is proposed, which models spatio-temporal constraints of video sequence. In order to improve the segmentation quality, the weights of spatio-temporal con- straints are adaptively updated by on-line learning for HCRFs. Shadows are the factors affecting segmentation quality. To separate foreground objects from the shadows they cast, linear transform for Gaussian distribution of the background is adopted to model the shadow. The experimental results demonstrated that the error ratio of our algorithm is reduced by 23% and 19% respectively, compared with the Gaussian mixture model (GMM) and spatio-temporal Markov random fields (MRFs).

Enhanced Identifying Gene Names from Biomedical Literature with Conditional Random Fields

Identifying gene names is an attractive research area of biology computing. However, accurate extraction of gene names is a challenging task with the lack of conventions for describing gene names. We devise a systematical architecture and apply the model using conditional random fields （CRFs） for extracting gene names from Medline. In order to improve the performance, biomedical ontology features are inserted into the model and post processing including boundary adjusting and word filter is presented to solve name overlapping problem and remove false positive single words. Pure string match method, baseline CRFs, and CRFs with our methods are applied to human gene names and HIV gene names extraction respectively in 1100 abstracts of Medline and their performances are contrasted. Results show that CRFs are robust for unseen gene names. Furthermore, CRFs with our methods outperforms other methods with precision 0.818 and recall 0.812.

A Remote Sensing Image Semantic Segmentation Method by Combining Deformable Convolution with Conditional Random Fields

Currently,deep convolutional neural networks have made great progress in the field of semantic segmentation.Because of the fixed convolution kernel geometry,standard convolution neural networks have been limited the ability to simulate geometric transformations.Therefore,a deformable convolution is introduced to enhance the adaptability of convolutional networks to spatial transformation.Considering that the deep convolutional neural networks cannot adequately segment the local objects at the output layer due to using the pooling layers in neural network architecture.To overcome this shortcoming,the rough prediction segmentation results of the neural network output layer will be processed by fully connected conditional random fields to improve the ability of image segmentation.The proposed method can easily be trained by end-to-end using standard backpropagation algorithms.Finally,the proposed method is tested on the ISPRS dataset.The results show that the proposed method can effectively overcome the influence of the complex structure of the segmentation object and obtain state-of-the-art accuracy on the ISPRS Vaihingen 2D semantic labeling dataset.

Fast Chinese syntactic parsing method based on conditional random fields

A fast method for phrase structure grammar analysis is proposed based on conditional ran- dom fields （CRF）. The method trains several CRF classifiers for recognizing the phrase nodes at dif- ferent levels, and uses the bottom-up to connect the recognized phrase nodes to construct the syn- tactic tree. On the basis of Beijing forest studio Chinese tagged corpus, two experiments are de- signed to select the training parameters and verify the validity of the method. The result shows that the method costs 78. 98 ms and 4. 63 ms to train and test a Chinese sentence of 17. 9 words. The method is a new way to parse the phrase structure grammar for Chinese, and has good generalization ability and fast speed.

Extracting 3D model feature lines based on conditional random fields

We propose a 3D model feature line extraction method using templates for guidance. The 3D model is first projected into a depth map, and a set of candidate feature points are extracted. Then, a conditional random fields (CRF) model is established to match the sketch points and the candidate feature points. Using sketch strokes, the candidate feature points can then be connected to obtain the feature lines, and using a CRF-matching model, the 2D image shape similarity features and 3D model geometric features can be effectively integrated. Finally, a relational metric based on shape and topological similarity is proposed to evaluate the matching results, and an iterative matching process is applied to obtain the globally optimized model feature lines. Experimental results showed that the proposed method can extract sound 3D model feature lines which correspond to the initial sketch template.

Scaling Conditional Random Fields by One-Against-the-Other Decomposition

As a powerful sequence labeling model, conditional random fields （CRFs） have had successful applications in many natural language processing （NLP） tasks. However, the high complexity of CRFs training only allows a very small tag （or label） set, because the training becomes intractable as the tag set enlarges. This paper proposes an improved decomposed training and joint decoding algorithm for CRF learning. Instead of training a single CRF model for all tags, it trains a binary sub-CRF independently for each tag. An optimal tag sequence is then produced by a joint decoding algorithm based on the probabilistic output of all sub-CRFs involved. To test its effectiveness, we apply this approach to tackling Chinese word segmentation （CWS） as a sequence labeling problem. Our evaluation shows that it can reduce the computational cost of this language processing task by 40-50% without any significant performance loss on various large-scale data sets.

2D Correlative-Chain Conditional Random Fields for Semantic Annotation of Web Objects

Semantic annotation of Web objects is a key problem for Web information extraction. The Web contains an abundance of useful semi-structured information about real world objects, and the empirical study shows that strong two-dimensional sequence characteristics and correlative characteristics exist for Web information about objects of the same type across different Web sites. Conditional Random Fields （CRFs） are the state-of-the-art approaches taking the sequence characteristics to do better labeling. However, as the appearance of correlative characteristics between Web object elements, previous CRFs have their limitations for semantic annotation of Web objects and cannot deal with the long distance dependencies between Web object elements efficiently. To better incorporate the long distance dependencies, on one hand, this paper describes long distance dependencies by correlative edges, which are built by making good use of structured information and the characteristics of records from external databases; and on the other hand, this paper presents a two-dimensional Correlative-Chain Conditional Random Fields （2DCC-CRFs） to do semantic annotation of Web objects. This approach extends a classic model, two-dimensional Conditional Random Fields （2DCRFs）, by adding correlative edges. Experimental results using a large number of real-world data collected from diverse domains show that the proposed approach can significantly improve the semantic annotation accuracy of Web objects.

Characterizing large-scale weak interlayer shear zones using conditional random field theory

The shear behavior of large-scale weak intercalation shear zones(WISZs)often governs the stability of foundations,rock slopes,and underground structures.However,due to their wide distribution,undulating morphology,complex fabrics,and varying degrees of contact states,characterizing the shear behavior of natural and complex large-scale WISZs precisely is challenging.This study proposes an analytical method to address this issue,based on geological fieldwork and relevant experimental results.The analytical method utilizes the random field theory and Kriging interpolation technique to simplify the spatial uncertainties of the structural and fabric features for WISZs into the spatial correlation and variability of their mechanical parameters.The Kriging conditional random field of the friction angle of WISZs is embedded in the discrete element software 3DEC,enabling activation analysis of WISZ C2 in the underground caverns of the Baihetan hydropower station.The results indicate that the activation scope of WISZ C2 induced by the excavation of underground caverns is approximately 0.5e1 times the main powerhouse span,showing local activation.Furthermore,the overall safety factor of WISZ C2 follows a normal distribution with an average value of 3.697.

Rockhead profile simulation using an improved generation method of conditional random field

Rockhead profile is an important part of geological profiles and can have significant impacts on some geotechnical engineering practice,and thus,it is necessary to establish a useful method to reverse the rockhead profile using site investigation results.As a general method to reflect the spatial distribution of geo-material properties based on field measurements,the conditional random field(CRF)was improved in this paper to simulate rockhead profiles.Besides,in geotechnical engineering practice,measurements are generally limited due to the limitations of budget and time so that the estimation of the mean value can have uncertainty to some extent.As the Bayesian theory can effectively combine the measurements and prior information to deal with uncertainty,CRF was implemented with the aid of the Bayesian framework in this study.More importantly,this simulation procedure is achieved as an analytical solution to avoid the time-consuming sampling work.The results show that the proposed method can provide a reasonable estimation about the rockhead depth at various locations against measurement data and as a result,the subjectivity in determining prior mean can be minimized.Finally,both the measurement data and selection of hyper-parameters in the proposed method can affect the simulated rockhead profiles,while the influence of the latter is less significant than that of the former.

Conditional Random Field Tracking Model Based on a Visual Long Short Term Memory Network

In dense pedestrian tracking,frequent object occlusions and close distances between objects cause difficulty when accurately estimating object trajectories.In this study,a conditional random field tracking model is established by using a visual long short term memory network in the three-dimensional(3D)space and the motion estimations jointly performed on object trajectory segments.Object visual field information is added to the long short term memory network to improve the accuracy of the motion related object pair selection and motion estimation.To address the uncertainty of the length and interval of trajectory segments,a multimode long short term memory network is proposed for the object motion estimation.The tracking performance is evaluated using the PETS2009 dataset.The experimental results show that the proposed method achieves better performance than the tracking methods based on the independent motion estimation.

Exploiting PLSA model and conditional random field for refining image annotation

This paper presents a new method for refining image annotation by integrating probabilistic la- tent semantic analysis （PLSA） with conditional random field （CRF）. First a PLSA model with asymmetric modalities is constructed to predict a candidate set of annotations with confidence scores, and then model semantic relationship among the candidate annotations by leveraging conditional ran- dom field. In CRF, the confidence scores generated lay the PLSA model and the Fliekr distance be- tween pairwise candidate annotations are considered as local evidences and contextual potentials re- spectively. The novelty of our method mainly lies in two aspects ： exploiting PLSA to predict a candi- date set of annotations with confidence scores as well as CRF to further explore the semantic context among candidate annotations for precise image annotation. To demonstrate the effectiveness of the method proposed in this paper, an experiment is conducted on the standard Corel dataset and its re- sults are ＇compared favorably with several state-of-the-art approaches.

An Image Segmentation Algorithm Based on a Local Region Conditional Random Field Model

To reduce the computation cost of a combined probabilistic graphical model and a deep neural network in semantic segmentation, the local region condition random field (LRCRF) model is investigated which selectively applies the condition random field (CRF) to the most active region in the image. The full convolutional network structure is optimized with the ResNet-18 structure and dilated convolution to expand the receptive field. The tracking networks are also improved based on SiameseFC by considering the frame relations in consecutive-frame traffic scene maps. Moreover, the segmentation results of the greyscale input data sets are more stable and effective than using the RGB images for deep neural network feature extraction. The experimental results show that the proposed method takes advantage of the image features directly and achieves good real-time performance and high segmentation accuracy.

STABC-IR:An air target intention recognition method based on bidirectional gated recurrent unit and conditional random field with space-time attention mechanism

The battlefield environment is changing rapidly,and fast and accurate identification of the tactical intention of enemy targets is an important condition for gaining a decision-making advantage.The current Intention Recognition(IR)method for air targets has shortcomings in temporality,interpretability and back-and-forth dependency of intentions.To address these problems,this paper designs a novel air target intention recognition method named STABC-IR,which is based on Bidirectional Gated Recurrent Unit(Bi GRU)and Conditional Random Field(CRF)with Space-Time Attention mechanism(STA).First,the problem of intention recognition of air targets is described and analyzed in detail.Then,a temporal network based on Bi GRU is constructed to achieve the temporal requirement.Subsequently,STA is proposed to focus on the key parts of the features and timing information to meet certain interpretability requirements while strengthening the timing requirements.Finally,an intention transformation network based on CRF is proposed to solve the back-and-forth dependency and transformation problem by jointly modeling the tactical intention of the target at each moment.The experimental results show that the recognition accuracy of the jointly trained STABC-IR model can reach 95.7%,which is higher than other latest intention recognition methods.STABC-IR solves the problem of intention transformation for the first time and considers both temporality and interpretability,which is important for improving the tactical intention recognition capability and has reference value for the construction of command and control auxiliary decision-making system.

Horizontal convergence reconstruction in the longitudinal direction for shield tunnels based on conditional random field

Tunnel horizontal convergence monitoring is essential to ensure the operation safety.However,only a few representative tunnel sec-tions are chosen for monitoring due to the cost limitation.It is difficult to capture the horizontal convergence of each tunnel ring with limited measurements.Confronted with this difficulty,the paper proposes a horizontal convergence reconstruction method based on the measurements of deployed sensors.The tunnel horizontal convergence along the longitudinal direction is seen as a one-dimensional sta-tionary and ergodic random field.The reconstruction problem is then transformed into the generation of conditional random fields.Monte Carlo simulation is adopted to generate possible realizations and the mean of realizations is considered as the maximum likeli-hood reconstruction.Error analysis proves the effectiveness of the proposed reconstruction method.The proposed method is proved to be applicable in reconstructing the time-variant horizontal convergence and is verified by the monitoring results of the shield tunnel of Shanghai Metro Line 2.The effect of sensor numbers is parametrically studied,and an optimal sensor placement scheme is decided.Additional sensors placed at the deformation drastically changed location can significantly improve the performance of the proposed method.

高级地图匹配算法:研究现状和趋势

地图匹配是许多位置服务与轨迹挖掘应用的基础.随着定位技术和位置服务应用的发展,地图匹配研究不断演进,从早期基于高采样率GPS(Global Position System)的实时匹配,到近期基于低采样率GPS轨迹的离线匹配、再到当前非GPS定位数据或高精度地图匹配。迄今已有许多地图匹配算法相继提出,但鲜有研究对这些算法进行全面总结.为此,对近十年提出的地图匹配算法进行调研,归纳出地图匹配算法的统一框架及常用时空特征.从模型或实现技术角度分类发现:现有算法大都采用HMM(Hidden Markov Model)模型,其次是最大权重模型;深度学习技术近期开始用于地图匹配,将是未来高精度地图匹配研究的趋势.

Integrating Multi-Source Web Records into Relational Database

How to integrate heterogeneous semi-structured Web records into relational database is an important and challengeable research topic. An improved model of conditional random fields was presented to combine the learning of labeled samples and unlabeled database records in order to reduce the dependence on tediously hand-labeled training data. The pro- posed model was used to solve the problem of schema matching between data source schema and database schema. Experimental results using a large number of Web pages from diverse domains show the novel approach＇s effectiveness.