Semantic Matching Method Research Articles

Browsing target extraction and spatiotemporal preference mining from the complex virtual trajectories

Public Map Service Platforms (PMSPs) aggregate and disseminate the earth observation data. Leveraging spatiotemporal preference patterns derived from browsing targets within complex virtual trajectories on PMSPs aids in constructing user-profiles and comprehending their intentions. However, complex virtual trajectories, characterized by numerous trajectory points and overlapping pyramidal spatial structures, introduce inefficiencies and inaccuracies during browsing target extraction. To mitigate this, we propose an Optimized Spatial Structure Segmentation (OSSS) method that divides complex virtual trajectories into sub-trajectories with simplified spatial structures, enhancing the efficiency of browsing target extraction. Spatiotemporal reconstruction of these sub-trajectories establishes sequences of browsing targets, revealing patterns of interest transitions. Moreover, recognizing the spatial uncertainty inherent in complex virtual trajectories, which results in imprecise matching between browsing targets and spatial features, we introduce a spatial co-occurrence semantic modeling approach. This involves constructing a POI semantic space and introducing a semantic similarity matching method to reduce spatial uncertainty and refine the accuracy of mining spatiotemporal preference patterns. We evaluate these methods using real-world data from Tianditu. Results demonstrate that the OSSS improves extraction efficiency by 3.45 times and accuracy by 18.84%. Additionally, the semantic similarity approach combined with spatial co-occurrence effectively mitigates spatial uncertainty. This research contributes to advancing the intelligence of PMSPs.

An efficient long-text semantic retrieval approach via utilizing presentation learning on short-text

Although the short-text retrieval model by BERT achieves significant performance improvement, research on the efficiency and performance of long-text retrieval still faces challenges. Therefore, this study proposes an efficient long-text retrieval model based on BERT (called LTR-BERT). This model achieves speed improvement while retaining most of the long-text retrieval performance. In particular, The LTR-BERT model is trained by using the relevance between short texts. Then, the long text is segmented and stored off-line. In the retrieval stage, only the coding of the query and the matching scores are calculated, which speeds up the retrieval. Moreover, a query expansion strategy is designed to enhance the representation of the original query and reserve the encoding region for the query. It is beneficial for learning missing information in the representation stage. The interaction mechanism without training parameters takes into account the local semantic details and the whole relevance to ensure the accuracy of retrieval and further shorten the response time. Experiments are carried out on MS MARCO Document Ranking dataset, which is specially designed for long-text retrieval. Compared with the interaction-focused semantic matching method by BERT-CLS, the MRR@10 values of the proposed LTR-BERT method are increased by 2.74%. Moreover, the number of documents processed per millisecond increased by 333 times.

Adaptive Semantic Matching in a Multilingual Context

In an increasingly multilingual digital world, information management tools must support the simultaneous use and matching of multiple natural languages. A prerequisite for this is that the underlying database engine seamlessly processes multilingual data across languages. However, most natural language processing-based techniques have focused on developing monolingual matching algorithms, often ignoring context knowledge and external domain-based sources, which lead to incomplete and inaccurate matching results in a multilingual environment. The purpose of this study is to propose an adaptive semantic matching method with context knowledge and user involvement as two new dimensions for matching the semantically related entities ontologies. We present a comprehensive evaluation of our solution by applying it in a multilingual e-commerce platform case study, which performed well on matching accuracy.

Adversarial example detection using semantic graph matching

Deep neural networks have recently been found to be vulnerable to adversarial examples, which can deceive attacked models with high confidence. This has given rise to significant security threats and raised doubts about the reliability of deploying deep learning models in security-critical domains. Therefore, effectively dealing with various adversarial examples has become an essential but challenging requirement. Adversarial example detection can predict the existence of adversarial examples in advance. However, existing detection methods are usually restricted to specific attacks, lacking generalization and decision-making bases. In this paper, we discover that the common characteristic of adversarial examples is to alter the semantic information recognized by models, which can effectively distinguish adversarial examples and provide interpretability. Based on this perspective, we propose a semantic graph matching (SeMatch) method to execute attack-agnostic adversarial example detection. SeMatch detects adversarial examples by comparing the constructed semantic graphs with the semantic graph prototypes of their predicted classes and further corrects their classification results. Experimental results demonstrate that SeMatch can effectively detect and classify adversarial examples in several attack settings, achieving an average detection and classification accuracy of 96.01% and 89.71%, respectively. When applied to unknown attack scenarios, SeMatch is more effective and interpretable than state-of-the-art methods.

Street‐level traffic flow and context sensing analysis through semantic integration of multisource geospatial data

AbstractSensing urban spaces from multisource geospatial data is vital to understanding the transportation system in the urban context. However, the complexity of urban context and its indirect interaction with traffic flow deepen the difficulty of exploring their relationship. This study proposes a geo‐semantic framework first to generate semantic representations of multi‐hierarchical urban context and street‐level traffic flow, and then investigate their mutual correlation and predictability using a novel semantic matching method. The results demonstrate that each street is associated with its multi‐hierarchical spatial signatures of urban context and street‐level temporal signatures of traffic flow. The correlation between urban context and traffic flow displays higher values after semantic matching than those in multi‐hierarchies. Moreover, we found that utilizing traffic flow to predict urban context results in better accuracy than the reversed prediction. The results of signature analysis and relationship exploration can contribute to a deeper understanding of context‐aware transportation research.

Indoor–Outdoor Point Cloud Alignment Using Semantic–Geometric Descriptor

Aligning indoor and outdoor point clouds is a challenging problem since the overlapping area is usually limited, thus resulting in a lack of correspondence features. The windows and doors can be observed from both sides and are usually utilized as shared features to make connections between indoor and outdoor models. However, the registration performance using the geometric features of windows and doors is limited due to the considerable number of extracted features and the mismatch of similar features. This paper proposed an indoor/outdoor alignment framework with a semantic feature matching method to solve the problem. After identifying the 3D window and door instances from the point clouds, a novel semantic–geometric descriptor (SGD) is proposed to describe the semantic information and the spatial distribution pattern of the instances. The best object match is identified with an improved Hungarian algorithm using indoor and outdoor SGDs. The matching method is effective even when the numbers of objects are not equal in the indoor and outdoor models, which is robust to measurement occlusions and feature outliers. The experimental results conducted in the collected dataset and the public dataset demonstrated that the proposed method could identify accurate object matches under complicated conditions, and the alignment accuracy reached the centimeter level.

LCR-SMM: Large Convergence Region Semantic Map Matching Through Expectation Maximization

The matching and fusion of local maps generated by multiple robots can greatly enhance the performance of relative localization and collaborative mapping. Currently, existing semantic matching methods are partly based on classical iterative closet point, which typically fails in cases with large initial errors. What’s more, current semantic matching algorithms have high computation complexity in optimizing the transformation matrix. To address the challenge of large initial errors and low matching efficiency, this article proposes a novel large convergence region semantic map matching algorithm. The key novelty of this work is the designing of the initial transformation optimization algorithm and the probabilistic registration model to increase the convergence region. To reduce the initial error before the iteration process, the initial transformation matrix is optimized by estimating the credibility of the data association. At the same time, a factor reflecting the uncertainty of the initial error is calculated and introduced to the formulation of the probabilistic registration model, thereby accelerating the convergence process. The proposed algorithm is performed on public datasets and compared with existing methods, demonstrating the significant improvement in terms of matching accuracy and robustness.

Distantly Supervised Named Entity Recognition with Self-Adaptive Label Correction

Named entity recognition has achieved remarkable success on benchmarks with high-quality manual annotations. Such annotations are labor-intensive and time-consuming, thus unavailable in real-world scenarios. An emerging interest is to generate low-cost but noisy labels via distant supervision, hence noisy label learning algorithms are in demand. In this paper, a unified self-adaptive learning framework termed Self-Adaptive Label cOrrection (SALO) is proposed. SALO adaptively performs a label correction process, both in an implicit and an explicit manners, turning noisy labels into correct ones, thus benefiting model training. The experimental results on four benchmark datasets demonstrated the superiority of SALO over the state-of-the-art distantly supervised methods. Moreover, a better version of noisy labels by ensembling several semantic matching methods was built. Experiments were carried out and consistent improvements were observed, validating the generalization of the proposed SALO.

Automatic SNOMED CT coding of Chinese clinical terms via attention-based semantic matching

BackgroundA considerable amount of meaningful information is routinely recorded in Chinese clinical data in text format, referred to as Chinese clinical terms. The lack of coding is a major difficulty hindering the application of clinical terms. SNOMED CT is a widely used and comprehensive clinical health care terminology collection because of its coverage, granularity, clinical orientation, and logical underpinning. It is useful and efficient for automatically assigning SNOMED CT codes to Chinese clinical terms, but it still faces several problems. Current cross-language clinical term matching studies rely on external resources, such as machine translation and rule-based methods. Semantic matching methods have achieved strong performance on text matching, but few studies have been done on cross-language clinical term matching. We present an effective attention-based semantic matching algorithm to automatically cross-language code Chinese clinical terms with SNOMED CT. MethodFirstly, BERT was used to turn the input into word embedding. Then, the word embeddings were encoded through a BiLSTM with self-attention to focus on capturing distant relationships among words with different weights depending on their contribution to semantic matching. Then, decomposable attention was used to make semantic matching trivially parallelizable to speed up calculation. Finally, fully connected layers and a sigmoid were utilized to output matching results. ResultsThe 29,960 manually coded Chinese clinical terms, 30,040 unmatched Chinese clinical terms and SNOMED CT codes were collected to evaluate the proposed method. Compared with the existing semantic matching method, the proposed approach achieves state-of-the-art results demonstrating the effectiveness of the method with an accuracy of 0.905, a precision of 0.856, a recall of 0.518, and an F-measure of 0.645. The proposed Chinese-English bilingual term mapping, Chinese character-level and word-level encoder, English word-level encoder, BERT model, and attention mechanism performed better than other methods. ConclusionThe proposed automatic SNOMED CT coding approach of Chinese clinical terms via attention-based semantic matching can improve the performance of automated SNOMED CT code assignment for Chinese clinical terms and improve the efficiency of the code assignment.

Image Captioning with multi-level similarity-guided semantic matching

Image Captioning is a cross-modal task that needs to automatically generate coherent natural sentences to describe the image contents. Due to the large gap between vision and language modalities, most of the existing methods have the problem of inaccurate semantic matching between images and generated captions. To solve the problem, this paper proposes a novel multi-level similarity-guided semantic matching method for image captioning, which can fuse local and global semantic similarities to learn the latent semantic correlation between images and generated captions. Specifically, we extract the semantic units containing fine-grained semantic information of images and generated captions, respectively. Based on the comparison of the semantic units, we design a local semantic similarity evaluation mechanism. Meanwhile, we employ the CIDEr score to characterize the global semantic similarity. The local and global two-level similarities are finally fused using the reinforcement learning theory, to guide the model optimization to obtain better semantic matching. The quantitative and qualitative experiments on large-scale MSCOCO dataset illustrate the superiority of the proposed method, which can achieve fine-grained semantic matching of images and generated captions.

Deep-learning-based automated terminology mapping in OMOP-CDM.

Accessing medical data from multiple institutions is difficult owing to the interinstitutional diversity of vocabularies. Standardization schemes, such as the common data model, have been proposed as solutions to this problem, but such schemes require expensive human supervision. This study aims to construct a trainable system that can automate the process of semantic interinstitutional code mapping. To automate mapping between source and target codes, we compute the embedding-based semantic similarity between corresponding descriptive sentences. We also implement a systematic approach for preparing training data for similarity computation. Experimental results are compared to traditional word-based mappings. The proposed model is compared against the state-of-the-art automated matching system, which is called Usagi, of the Observational Medical Outcomes Partnership common data model. By incorporating multiple negative training samples per positive sample, our semantic matching method significantly outperforms Usagi. Its matching accuracy is at least 10% greater than that of Usagi, and this trend is consistent across various top-k measurements. The proposed deep learning-based mapping approach outperforms previous simple word-level matching algorithms because it can account for contextual and semantic information. Additionally, we demonstrate that the manner in which negative training samples are selected significantly affects the overall performance of the system. Incorporating the semantics of code descriptions more significantly increases matching accuracy compared to traditional text co-occurrence-based approaches. The negative training sample collection methodology is also an important component of the proposed trainable system that can be adopted in both present and future related systems.

MEM-KGC: Masked Entity Model for Knowledge Graph Completion With Pre-Trained Language Model

The knowledge graph completion (KGC) task aims to predict missing links in knowledge graphs. Recently, several KGC models based on translational distance or semantic matching methods have been proposed and have achieved meaningful results. However, existing models have a significant shortcoming–they cannot train entity embedding when an entity does not appear in the training phase. As a result, such models use randomly initialized embeddings for entities that are unseen in the training phase and cause a critical decrease in performance during the test phase. To solve this problem, we propose a new approach that performs KGC task by utilizing the masked language model (MLM) that is used for a pre-trained language model. Given a triple ( head entity , relation , tail entity ), we mask the tail entity and consider the head entity and the relation as a context for the tail entity. The model then predicts the masked entity from among all entities. Then, the task is conducted by the same process as an MLM, which predicts a masked token with a given context of tokens. Our experimental results show that the proposed model achieves significantly improved performances when unseen entities appear during the test phase and achieves state-of-the-art performance on the WN18RR dataset.

Semantic Matching Efficiency of Supply and Demand Text on Cross‐Border E‐Commerce Online Technology Trading Platforms

With the innovation of global trade business models, more and more foreign trade companies are transforming and developing in the direction of cross‐border e‐commerce. However, due to the limitation of platform language processing and analysis technology, foreign trade companies encounter many bottlenecks in the process of transformation and upgrading. From the perspective of the semantic matching efficiency of e‐commerce platforms, this paper improves the logical and technical problems of cross‐border e‐commerce in the operation process and uses semantic matching efficiency as the research object to conduct experiments on the QQP dataset. We propose a graph network text semantic analysis model TextSGN based on semantic dependency analysis for the problem that the existing text semantic matching method does not consider the semantic dependency information between words in the text and requires a large amount of training data. The model first analyzes the semantic dependence of the text and performs word embedding and one‐hot encoding on the nodes (single words) and edges (dependencies) in the semantic dependence graph. On this basis, in order to quickly mine semantic dependencies, an SGN network block is proposed. The network block defines the way of information transmission from the structural level to update the nodes and edges in the graph, thereby quickly mining semantics dependent information allows the network to converge faster, train classification models on multiple public datasets, and perform classification tests. The experimental results show that the accuracy rate of TextSGN model in short text classification reaches 95.2%, which is 3.6% higher than the suboptimal classification method; the accuracy rate is 86.16%, the F1 value is 88.77%, and the result is better than other methods.

Toward Translating Raw Indoor Positioning Data into Mobility Semantics

Indoor mobility analyses are increasingly interesting due to the rapid growth of raw indoor positioning data obtained from IoT infrastructure. However, high-level analyses are still in urgent need of a concise but semantics-oriented representation of the mobility implied by the raw data. This work studies the problem of translating raw indoor positioning data into mobility semantics that describe a moving object’s mobility event (What) someplace (Where) at some time (When). The problem is non-trivial mainly because of the inherent errors in the uncertain, discrete raw data. We propose a three-layer framework to tackle the problem. In the cleaning layer, we design a cleaning method that eliminates positioning data errors by considering indoor mobility constraints. In the annotation layer, we propose a split-and-match approach to annotate mobility semantics on the cleaned data. The approach first employs a density-based splitting method to divide positioning sequences into split snippets according to underlying mobility events, followed by a semantic matching method that makes proper annotations for split snippets. In the complementing layer, we devise an inference method that makes use of the indoor topology and the mobility semantics already obtained to recover the missing mobility semantics. The extensive experiments demonstrate that our solution is efficient and effective on both real and synthetic data. For typical queries, our solution’s resultant mobility semantics lead to more precise answers but incur less execution time than alternatives.

Salient context-based semantic matching for information retrieval

Neural networks provide new possibilities to uncover semantic relationships between words by involving contextual information, and further a way to learn the matching pattern from document-query word contextual similarity matrix, which has brought promising results in IR. However, most neural IR methods rely on the conventional word-word matching framework for finding a relevant document for a query. Its effect is limited due to the wide gap between the lengths of query and document. To address this problem, we propose a salient context-based semantic matching (SCSM) method to build a bridge between query and document. Our method locates the most relevant context in the document using a shifting window with adapted length and then calculates the relevance score within it as the representation of the document. We define the notion of contextual salience and the corresponding measures to calculate the relevance of a context to a given query, in which the interaction between the query and the context is modeled by semantic similarity. Experiments on various collections from TREC show the effectiveness of our model as compared to the state-of-the-art methods.

A Pseudo-relevance feedback framework combining relevance matching and semantic matching for information retrieval

Pseudo-relevance feedback (PRF) is a well-known method for addressing the mismatch between query intention and query representation. Most current PRF methods consider relevance matching only from the perspective of terms used to sort feedback documents, thus possibly leading to a semantic gap between query representation and document representation. In this work, a PRF framework that combines relevance matching and semantic matching is proposed to improve the quality of feedback documents. Specifically, in the first round of retrieval, we propose a reranking mechanism in which the information of the exact terms and the semantic similarity between the query and document representations are calculated by bidirectional encoder representations from transformers (BERT); this mechanism reduces the text semantic gap by using the semantic information and improves the quality of feedback documents. Then, our proposed PRF framework is constructed to process the results of the first round of retrieval by using probability-based PRF methods and language-model-based PRF methods. Finally, we conduct extensive experiments on four Text Retrieval Conference (TREC) datasets. The results show that the proposed models outperform the robust baseline models in terms of the mean average precision (MAP) and precision P at position 10 (P@10), and the results also highlight that using the combined relevance matching and semantic matching method is more effective than using relevance matching or semantic matching alone in terms of improving the quality of feedback documents.

Establishment of Petrochemical Process Security Simulation and Emergency Drill Platform

The petrochemical process is universally featured in large production scale, long process and multiple procedures, which lead to high difficulty in security simulation system establishment for petrochemical process and formulation of emergency plan. This paper puts forward a construction method for security simulation system modeling platform for petrochemical process, and the platform could provide the function of emergency drill. The platform could rapidly build simulation model through mechanism modeling and data modeling, and apply knowledge graph technology and semantic feature matching method to automatically analyze different emergency plans to acquire formal definition of plan and realize automatic plan selection. Compared to traditional method, the platform proposed in this paper could simulate different accident scenes and acquire effective emergency plans, providing effective assistance for emergency disposal decision making.

Overcoming the Barriers That Obscure the Interlinking and Analysis of Clinical Data Through Harmonization and Incremental Learning.

Goal: To present a framework for data sharing, curation, harmonization and federated data analytics to solve open issues in healthcare, such as, the development of robust disease prediction models. Methods: Data curation is applied to remove data inconsistencies. Lexical and semantic matching methods are used to align the structure of the heterogeneous, curated cohort data along with incremental learning algorithms including class imbalance handling and hyperparameter optimization to enable the development of disease prediction models. Results: The applicability of the framework is demonstrated in a case study of primary Sjögren's Syndrome, yielding harmonized data with increased quality and more than 85% agreement, along with lymphoma prediction models with more than 80% sensitivity and specificity. Conclusions: The framework provides data quality, harmonization and analytics workflows that can enhance the statistical power of heterogeneous clinical data and enables the development of robust models for disease prediction.

An unsupervised approach for learning a Chinese IS-A taxonomy from an unstructured corpus

Taxonomies play an important role in various Natural Language Processing (NLP) tasks (e.g., text classification, information extraction and knowledge inference). However, due to the complexity and flexibility of the Chinese natural language, it is challenging to accurately learn a Chinese IS-A (C-IS-A) taxonomy from an unstructured corpus. In this paper, we propose an unsupervised C-IS-A taxonomy learning approach by analyzing a given unstructured corpus. Our approach uses three main steps to automatically learn a C-IS-A taxonomy. First, our approach extracts high-quality C-IS-A seed relations via semantic iterative pattern-based matching and syntactic methods. Second, our approach utilizes an unsupervised taxonomic semantic-clique-based method to increase the coverage of the C-IS-A taxonomy. As the core component of our approach, we exploit the extracted C-IS-A seed relations to construct taxonomic semantic cliques and use the context of the cliques and multi-concept co-occurrence information to infer potential novel C-IS-A relations. Last, a two-step relation detection strategy is proposed to remove potentially incorrect C-IS-A relations, which can substantially improve the accuracy of the learned taxonomy. We implement our approach on four Chinese unstructured corpora and evaluate it in terms of precision, coverage, time cost and the effects of the subcomponents. The evaluation results demonstrate that our approach is an effective method that outperforms the state-of-the-art compared approaches.

Combining Fact Extraction and Verification with Neural Semantic Matching Networks

The increasing concern with misinformation has stimulated research efforts on automatic fact checking. The recentlyreleased FEVER dataset introduced a benchmark factverification task in which a system is asked to verify a claim using evidential sentences from Wikipedia documents. In this paper, we present a connected system consisting of three homogeneous neural semantic matching models that conduct document retrieval, sentence selection, and claim verification jointly for fact extraction and verification. For evidence retrieval (document retrieval and sentence selection), unlike traditional vector space IR models in which queries and sources are matched in some pre-designed term vector space, we develop neural models to perform deep semantic matching from raw textual input, assuming no intermediate term representation and no access to structured external knowledge bases. We also show that Pageview frequency can also help improve the performance of evidence retrieval results, that later can be matched by using our neural semantic matching network. For claim verification, unlike previous approaches that simply feed upstream retrieved evidence and the claim to a natural language inference (NLI) model, we further enhance the NLI model by providing it with internal semantic relatedness scores (hence integrating it with the evidence retrieval modules) and ontological WordNet features. Experiments on the FEVER dataset indicate that (1) our neural semantic matching method outperforms popular TF-IDF and encoder models, by significant margins on all evidence retrieval metrics, (2) the additional relatedness score and WordNet features improve the NLI model via better semantic awareness, and (3) by formalizing all three subtasks as a similar semantic matching problem and improving on all three stages, the complete model is able to achieve the state-of-the-art results on the FEVER test set (two times greater than baseline results).1