Semantic Similarity Evaluation Research Articles

Proactive safety hazard identification using visual–text semantic similarity for construction safety management

Automated safety management in construction can reduce injuries by identifying hazardous postures, actions, and missing personal protective equipment (PPE). However, existing computer vision (CV) methods have limitations in connecting recognition results to text-based safety rules. To address this issue, this paper presents a multi-modal framework that bridges the gap between construction image monitoring and safety knowledge. The framework includes an image processing module that utilizes CV and dense image captioning techniques, and a text processing module that employs natural language processing for semantic similarity evaluation. Experiments showed a mean average precision of 49.6% in dense captioning and an F1 score of 74.3% in hazard identification. While the proposed framework demonstrates a promising multi-modal approach towards automated safety hazard identification and reasoning, improvements in dataset size and model performance are still needed to enhance its effectiveness in real-world applications.

Zero-shot Learning with Minimum Instruction to Extract Social Determinants and Family History from Clinical Notes using GPT Model.

Demographics, social determinants of health, and family history documented in the unstructured text within the electronic health records are increasingly being studied to understand how this information can be utilized with the structured data to improve healthcare outcomes. After the GPT models were released, many studies have applied GPT models to extract this information from the narrative clinical notes. Different from the existing work, our research focuses on investigating the zero-shot learning on extracting this information together by providing minimum information to the GPT model. We utilize de-identified real-world clinical notes annotated for demographics, various social determinants, and family history information. Given that the GPT model might provide text different from the text in the original data, we explore two sets of evaluation metrics, including the traditional NER evaluation metrics and semantic similarity evaluation metrics, to completely understand the performance. Our results show that the GPT-3.5 method achieved an average of 0.975 F1 on demographics extraction, 0.615 F1 on social determinants extraction, and 0.722 F1 on family history extraction. We believe these results can be further improved through model fine-tuning or few-shots learning. Through the case studies, we also identified the limitations of the GPT models, which need to be addressed in future research.

Semantic Similarity Based on Taxonomies

The evaluation of the semantic similarity of concepts organized according to taxonomies is a long-standing problem in computer science and has attracted great attention from researchers over the decades. In this regard, the notion of information content plays a key role, and semantic similarity measures based on it are still on the rise. In this review, we address the methods for evaluating the semantic similarity between either concepts or sets of concepts belonging to a taxonomy that, often, in the literature, adopt different notations and formalisms. The results of this systematic literature review provide researchers and academics with insight into the notions that the methods discussed have in common through the use of the same notation, as well as their differences, overlaps, and dependencies, and, in particular, the role of the notion of information content in the evaluation of semantic similarity. Furthermore, in this review, a comparative analysis of the methods for evaluating the semantic similarity between sets of concepts is provided.

A NOVEL SEMANTIC SIMILARITY SCORE FOR PROTEIN DATA ANALYSIS

Aim: A similarity evaluation measure for Gene Ontology GO terms is developed. Results: The proposed method takes into account the semantics hidden in ontologies or the term level information content, membership of term, and topology-based similarity measures. The proposed method is evaluated on positive and negative dataset of UniProt, Protein family clans and the Pearson’s correlation with other existing methods. Conclusion: The experimental results exhibited a major supremacy of the proposed method over other semantic similarity measures. HIGHLIGHTS:1. An improved approach for semantic similarity evaluation for GO terms based on the information content and the topological factors is developed.2. The proposed method shows highest correlation for MF (Molecular Function) ontology.

Manta ray optimized deep contextualized bi-directional long short-term memory based adaptive galactic swarm optimization for complex question answering

Complex question answering (CQA) is used for human knowledge answering and community questions answering. CQA system is essential to overcome the complexities present in the question answering system. The existing techniques ignores the queries structure and resulting a significant number of noisy queries. The complex queries, distributed knowledge, composite approaches, templates, and ambiguity are the common challenges faced by the CQA. To solve these issues, this paper presents a new manta ray foraging optimized deep contextualized bidirectional long-short term memory based adaptive galactic swarm optimization (MDCBiLSTMAGSO) for CQA. At first, the given input question is preprocessed and the similarity assessment is performed to eliminate the misclassification. Afterwards, the attained keywords are mapped into applicant results to improve the answer selection. Next, a new similarity approach named InfoSelectivity is introduced for semantic similarity evaluation based on the closeness among elements. Then, the relevant answers are classified through the MDCBiLSTM and optimized by a new manta ray foraging optimization (MRFO). Finally, adaptive galactic swarm optimization (AGSO) resultant is the best output. The proposed scheme is implemented on the JAVA platform and the outputs of designed approach achieved the better results when compared with the existing approaches in average accuracy (98.2%).

Calculation and Performance Evaluation of Text Similarity Based on Strong Classification Features

Abstract Based on the strong classification feature recognition algorithm, the calculation algorithm of a text semantic similarity is studied with the performance evaluation in this paper. In order to achieve a general algorithm for this function, the semantic function library based on a semantic recognition code as a comparison object is designed. It drives the algorithm modules of two fuzzy neuron deep convolution machine learning, and between these two processes of machine learning, a rigid algorithm based on Fourier transform frequency domain feature is extracted. Finally, a more complex machine learning general algorithm is realized by the use of external data fuzzy algorithm and de-fuzzy algorithm before and after the algorithm module. It is also a technical innovation in this paper. Through the performance evaluation based on the subjective evaluation of volunteers, it is found that the system focuses on the text semantic similarity evaluation of the Chinese language, and achieves a comparison result of 81.78% of the artificial judgment accuracy rate, and only 5.52% of the volunteers believe that the system judgment result is completely different from that of manual judgment.

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.

Exploring intrinsic information content models for addressing the issues of traditional semantic measures to evaluate verb similarity

Semantic similarity measures play an important role in many natural language processing and information retrieval activities. It is highly challenging to measure semantic similarity with higher accuracy. A notable branch of semantic similarity evaluation based on information content (IC) is popular in this aspect. Intrinsic information content (IIC) models are another wing of IC based evaluation. Both IC based and IIC based approaches majorly handled similarity evaluation of nouns. Research related to semantic similarity assessment of verb pairs are rarely discussed. To bridge this gap, this work examines various IC based, IIC based approaches on verb pairs. A detailed discussion of the existing measures and their drawbacks are mentioned in this work. Strategies based on information content, length and depth of the concepts are discussed and tested on benchmark datasets. Existing intrinsic information content models are enhanced by addressing various issues like (a) dealing concepts with no path in WordNet and (b) handling the synonym sets of verb concepts. Measures based on path length, intrinsic information content, combined strategies and non-linear strategies for verb pairs are thoroughly inspected. This paper also presents novel strategies to understand novel aspects that are not addressed before. The strategies are experimented by generating the synonym sets of required parts-of-speech which proved very effective in improving the correlation with human judgment. Results on benchmark datasets specify that the proposed approaches for verb similarity will be a guiding factor for understanding the natural language processing tasks.

Global and Local Information Adjustment for Semantic Similarity Evaluation

Semantic similarity evaluation is used in various fields such as question-and-answering and plagiarism testing, and many studies have been conducted into this problem. In previous studies using neural networks to evaluate semantic similarity, similarity has been measured using global information of sentence pairs. However, since sentences do not only have one meaning but a variety of meanings, using only global information can have a negative effect on performance improvement. Therefore, in this study, we propose a model that uses global information and local information simultaneously to evaluate the semantic similarity of sentence pairs. The proposed model can adjust whether to focus more on global information or local information through a weight parameter. As a result of the experiment, the proposed model can show that the accuracy is higher than existing models that use only global information.

Knowledge graph mining for realty domain using dependency parsing and QAT models

The real estate business has a lot of risks, and in order to minimize them, you need a lot of information from different sources. Systems based on natural language processing can help customers find this information more easily: question answering, information retrieval, etc. The existing method of question answering requires data aligned with possible questions, which are not easy to obtain, in contrast, the knowledge-graph provides structured information. In this paper, we propose semi-automated ontology generation for the realty domain and a subsequent method for information retrieval related to the knowledge-graph of this ontology. The first contribution is the method for relation extraction method based on dependency-parsing and semantic similarity evaluation, which allows us to form ontology for a particular domain. The second contribution is knowledge-graph completion method based on question answering over text neural network. Our experimental analysis shows the efficiency of the proposed approaches.

Community answer generation based on knowledge graph

Community Question Answering (CQA) has become an indispensable way for modern people to share and acquire knowledge. It allows users to ask questions, which will be answered by experienced users enthusiastically. By recording user operation logs, CQA has accumulated a large amount of valuable and complex data. However, askers must wait (usually for a long time) until other expert users answer their questions on social platforms. This will seriously affect the user experience. In this paper, we propose a Community Answer Generation method based on the Knowledge Graph, called CAGKG, to generate natural language answers automatically. Firstly, we extract the core phrases of posts to represent their semantics relations. Then, we model the user's knowledge background based on their action records. Finally, we query knowledge entities in a knowledge graph based on user background and question semantics, then convert them into natural language answers. Besides, we proposed a Phrase-based Answers Semantic Similarity Evaluation indicator, called PASSE, which focuses on the semantic similarity between texts instead of literal matching. To the best of our knowledge, it is the first work that utilizes the user knowledge and text semantics to improve the performance of CQA. Experiments on four real datasets (Stack Overflow, Super User, Mathematics, and Quora) show that CAGKG is superior to the state-of-the-art question answering frameworks. Compared with other answer evaluation indicators, PASSE is a promising indicator for evaluating semantic similarity.

A Semantic Similarity Evaluation for Healthcare Ontologies Matching to HL7 FHIR Resources.

Healthcare 4.0 demands healthcare data to be shaped into a common standardized and interoperable format for achieving more efficient data exchange. Most of the techniques addressing this domain are dealing only with specific cases of data transformation through the translation of healthcare data into ontologies, which usually result in clinical misinterpretations. Currently, ontology alignment techniques are used to match different ontologies based on specific string and semantic similarity metrics, where very little systematic analysis has been performed on which semantic similarity techniques behave better. For that reason, in this paper we are investigating on finding the most efficient semantic similarity technique, based on an existing approach that can transform any healthcare dataset into HL7 FHIR, through the translation of the latter into ontologies, and their matching based on syntactic and semantic similarities.

Mapping sentences to concept transferred space for semantic textual similarity

Semantic textual similarity ( $$\mathcal {STS}$$ ) seeks to assess the degree of semantic equivalence between two sentences or snippets of texts. Most methods of $$\mathcal {STS}$$ are based on word surface and deem words as meaning unrelated symbols, which makes these methods indiscriminative for ubiquitous conceptual association among words. Recently, concept transferred space (CTS) is proposed to solve word conceptual association problem. It is generated from the noun concepts with their IS-A relations in WordNet. However, the CTS-based model can only calculate nouns; as a result, a large number of words, i.e., verbs, adjectives, adverbs as well as out-of-vocabulary named entities (OOV NEs), are neglected, thus resulting in information loss in the semantic similarity evaluation. This paper presents ways to solve this problem: To involve words other than nouns, derivational links in WordNet are employed to associate verbs, adjectives, and adverbs with their corresponding noun concepts; to prevent information loss by OOV NEs, the increased quantity of information of them is predicted according to the tendency learned from known NEs. Moreover, to further improve the accuracy of the CTS-based model, we take the importance of different types of words into consideration by assigning corresponding weights for them. Experimental results suggest that the proposed comprehensive CTS-based model achieves significant improvement compared with the primitive one without the non-nominal words, OOV NEs, and word weights and also outperforms all the yearly state-of-the-art systems at the *SEM/SemEval 2013–2016 $$\mathcal {STS}$$ tasks. Additionally, at the SemEval 2017 $$\mathcal {STS}$$ task, our team with the comprehensive CTS-based model ranked the second and the first among all teams and on Track 1 dataset, respectively.

Pattern-based integration of system optimization in mechatronic system design

Model-Based Systems Engineering (MBSE) is a promising methodology for the design of complex mechatronic systems. There are some tools developed to support MBSE in complex system design and modeling. However, none of them has got the functionality of supporting system optimization. This work is precisely motivated by this gap and aims to develop effective methods to support automatic system optimization for MBSE. Specifically, a pattern-based method is proposed to support the integration of system optimization into mechatronic system design. In such a method, optimization problems, their solving methods and computation results are formally defined in each pattern based on the System Modeling Language (SysML). In addition, a model description scheme termed an optimization profile is proposed based on SysML to include the components for formalizing different kinds of optimization problems and optimization methods. After an optimization profile is created for an optimization problem, system optimization methods can be chosen automatically from the pattern library based on a semantic similarity evaluation. Then, optimization results are provided to users to support decision-making and the pattern library is updated using the relevant information obtained in this process. A system design example is used to demonstrate the feasibility and effectiveness of proposed methods.

Evaluation of semantic similarity for sentences in natural language by mathematical statistics methods

Subject of Research. The paper is focused on Wiktionary articles structural organization in the aspect of its usage as the base for semantic network. Wiktionary community references, article templates and articles markup features are analyzed. The problem of numerical estimation for semantic similarity of structural elements in Wiktionary articles is considered. Analysis of existing software for semantic similarity estimation of such elements is carried out; algorithms of their functioning are studied; their advantages and disadvantages are shown. Methods. Mathematical statistics methods were used to analyze Wiktionary articles markup features. The method of semantic similarity computing based on statistics data for compared structural elements was proposed.Main Results. We have concluded that there is no possibility for direct use of Wiktionary articles as the source for semantic network. We have proposed to find hidden similarity between article elements, and for that purpose we have developed the algorithm for calculation of confidence coefficients proving that each pair of sentences is semantically near. The research of quantitative and qualitative characteristics for the developed algorithm has shown its major performance advantage over the other existing solutions in the presence of insignificantly higher error rate. Practical Relevance. The resulting algorithm may be useful in developing tools for automatic Wiktionary articles parsing. The developed method could be used in computing of semantic similarity for short text fragments in natural language in case of algorithm performance requirements are higher than its accuracy specifications.

Discourse Analysis of Public Debates Using Corpus Linguistic Methodologies

The aim of this study is to develop a computational method of discourse analysis based on corpus semantics. The objective is to achieve an accurate understanding of the debate content and structure through hypotheses generation. As for verifying the hypotheses, the topic extraction and semantic similarity evaluation from the public debate minute corpus is examined by using a multimethod which includes TFIDF, T-VSM, and MDS. The main issue of public debate and the inconsistency level between participants’ utterance could be described by using the method. The methodology presented in this study is applied to a case example. Finally, the applicability of the proposed methodology to practical debates is discussed.