Semantic Similarity Measures Research Articles

Design creativity and the semantic analysis of conversations in the design studio

ABSTRACT The analysis of conversations during design activity can facilitate deeper insights into design thinking and its relation to creativity. A semantic analysis approach was employed to explore the semantic content of communication and information exchange between students and instructors. The goal was to examine design conversations in terms of abstraction, Polysemy, Information Content, and Semantic Similarity measures, and analyze their relation to the creativity of final solutions. These design outcomes were assessed according to their Originality, Usability, Feasibility, Overall Value, and Overall Creativity. Consequently, 35 design conversations from the 10th Design Thinking Research Symposium (DTRS10) dataset were analyzed. The main results showed that Information Content and Semantic Similarity predicted Originality, and Information Content alone predicted Overall Creativity. Likewise, ion predicted Feasibility, while Semantic Similarity, Information Content, and Polysemy predicted Overall Value. In context of instructors, Semantic Similarity predicted Usability, and Polysemy predicted Feasibility. For students, Semantic Similarity predicted Overall Value. On the whole, Semantic Similarity and Information Content were the most prolific measures, and therefore could be considered for promoting creativity in the design studio. The implications of using support tools such as automated systems are also discussed.

Semantic Technologies for Semantic Applications. Part 2. Models of Comparative Text Semantics

Both parts of this paper discuss the basic aspects of semantic computing, semantic technologies, and semantic applications applied to NL-text big data processing for knowledge extracting and decision making. The basic components of the corresponding systems and technologies are reviewed, which include ontologies and semantic models of their use, semantic resources, and semantic component. The semantic resources contain knowledge about the semantics and means for refinement of this semantics. The semantic component of the technology is used to formally describe the meaning of NL-entities and numerically evaluate their pairwise semantic similarity. The main focus of this part is on numerical models of pairwise semantic similarity of NL-entities. These models are important for solving tasks of text semantic clustering and classification and their various applications. Various types of semantic relatedness and semantic similarity measures for NL-entities in the context of semantic computing tasks are discussed and compared. Problems that constrain the practical use of semantic technologies for the development of semantic applications are analyzed.

Semantic Similarity for English and Arabic Texts: A Review

Semantic similarity is the task of measuring relations between sentences or words to determine the degree of similarity or resemblance. Several applications of natural language processing require semantic similarity measurement to achieve good results; these applications include plagiarism detection, text entailment, text summarisation, paraphrasing identification, and information extraction. Many researchers have proposed new methods to measure the semantic similarity of Arabic and English texts. In this research, these methods are reviewed and compared. Results show that the precision of the corpus-based approach exceeds 0.70. The precision of the descriptive feature-based technique is between 0.670 and 0.86, with a Pearson correlation coefficient of over 0.70. Meanwhile, the word embedding technique has a correlation of 0.67, and its accuracy is in the range 0.76–0.80. The best results are achieved by the feature-based approach.

RETRACTED: A Hybrid Semantic Similarity Measurement for Geospatial Entities

Semantic similarity plays a critical role in geospatial cognition, semantic interoperability, information integration and information retrieval and reasoning in geographic information science. Although some computational models for semantic similarity measurement have been proposed in literature, these models overlook spatial distribution characteristics or geometric features and pay little attention to the types and ranges of properties. This paper presents a novel semantic similarity measurement approach that employs a richer structured semantic description containing properties as well as relations. This approach captures the geo-semantic similarity more accurately and effectively by evaluating the contributions for ontological properties, measuring the effect of the relative position in the ontology hierarchy structure and computing the geometric feature similarity for geospatial entities. A water body ontology is used to illustrate the approach in a case study. A human-subject experiment was carried out and the experiment results shows that this proposed approach has a good performance based on the high correlation between its computed similarity results and human's judgements of similarity.

Measurement of Semantic Textual Similarity in Clinical Texts: Comparison of Transformer-Based Models.

BackgroundSemantic textual similarity (STS) is one of the fundamental tasks in natural language processing (NLP). Many shared tasks and corpora for STS have been organized and curated in the general English domain; however, such resources are limited in the biomedical domain. In 2019, the National NLP Clinical Challenges (n2c2) challenge developed a comprehensive clinical STS dataset and organized a community effort to solicit state-of-the-art solutions for clinical STS.ObjectiveThis study presents our transformer-based clinical STS models developed during this challenge as well as new models we explored after the challenge. This project is part of the 2019 n2c2/Open Health NLP shared task on clinical STS.MethodsIn this study, we explored 3 transformer-based models for clinical STS: Bidirectional Encoder Representations from Transformers (BERT), XLNet, and Robustly optimized BERT approach (RoBERTa). We examined transformer models pretrained using both general English text and clinical text. We also explored using a general English STS dataset as a supplementary corpus in addition to the clinical training set developed in this challenge. Furthermore, we investigated various ensemble methods to combine different transformer models.ResultsOur best submission based on the XLNet model achieved the third-best performance (Pearson correlation of 0.8864) in this challenge. After the challenge, we further explored other transformer models and improved the performance to 0.9065 using a RoBERTa model, which outperformed the best-performing system developed in this challenge (Pearson correlation of 0.9010).ConclusionsThis study demonstrated the efficiency of utilizing transformer-based models to measure semantic similarity for clinical text. Our models can be applied to clinical applications such as clinical text deduplication and summarization.

Multi-objective multi-view based search result clustering using differential evolution framework

Search Results Clustering (SRC) is a well-known problem in the field of information retrieval and refers to the clustering of web-snippets for a given query based on some similarity/dissimilarity measure. In this current study, we have posed Search Results Clustering problem as a multi-view clustering problem and solved it from an optimization point of view. Various views based on syntactic and semantic similarity measures were considered while performing the clustering. In contrast to existing algorithms, three new views based on word mover distance, textual-entailment, and universal sentence encoder, measuring semantics while performing clustering, are incorporated in our framework. Different quality measures computed on clusters generated by different views are optimized simultaneously using multi-objective binary differential evolution (MBDE) framework. MBDE comprises a set of solutions and each solution is composed of two parts corresponding to different views. An agreement index checking the accordance between partitionings of different views is also optimized to obtain a consensus partitioning. The proposed approach is automatic in nature as it is capable of detecting the number of clusters for any query in an automatic way. Experiments are performed on three benchmark multi-view datasets corresponding to web search results and evaluated using well-known F-measure metric. Results obtained illustrate that our approach outperforms state-of-the-art techniques.

Influence of the go-based semantic similarity measures in multi-objective gene clustering algorithm performance.

Using a prior biological knowledge of relationships and genetic functions for gene similarity, from repository such as the Gene Ontology (GO), has shown good results in multi-objective gene clustering algorithms. In this scenario and to obtain useful clustering results, it would be helpful to know which measure of biological similarity between genes should be employed to yield meaningful clusters that have both similar expression patterns (co-expression) and biological homogeneity. In this paper, we studied the influence of the four most used GO-based semantic similarity measures in the performance of a multi-objective gene clustering algorithm. We used four publicly available datasets and carried out comparative studies based on performance metrics for the multi-objective optimization field and clustering performance indexes. In most of the cases, using Jiang-Conrath and Wang similarities stand in terms of multi-objective metrics. In clustering properties, Resnik similarity allows to achieve the best values of compactness and separation and therefore of co-expression of groups of genes. Meanwhile, in biological homogeneity, the Wang similarity reports greater number of significant GO terms. However, statistical, visual, and biological significance tests showed that none of the GO-based semantic similarity measures stand out above the rest in order to significantly improve the performance of the multi-objective gene clustering algorithm.

Exploiting non-taxonomic relations for measuring semantic similarity and relatedness in WordNet

Various applications in computational linguistics and artificial intelligence employ semantic similarity to solve challenging tasks, such as word sense disambiguation, text classification, information retrieval, machine translation, and document clustering. To our knowledge, research to date rely solely on the taxonomic relation “ISA” to evaluate semantic similarity and relatedness between terms. This paper explores the benefits of using all types of non-taxonomic relations in large linked data, such as WordNet knowledge graph, to enhance existing semantic similarity and relatedness measures. We propose a holistic poly-relational approach based on a new relation-based information content and non-taxonomic-based weighted paths to devise a comprehensive semantic similarity and relatedness measure. To demonstrate the benefits of exploiting non-taxonomic relations in a knowledge graph, we used three strategies to deploy non-taxonomic relations at different granularity levels. We conduct experiments on four well-known gold standard datasets. The results of our proposed method demonstrate an improvement over the benchmark semantic similarity methods, including the state-of-the-art knowledge graph embedding techniques, that ranged from 3.8%–23.8%, 1.3%–18.3%, 31.8%–117.2%, and 19.1%–111.1%, on all gold standard datasets MC, RG, WordSim, and Mturk, respectively. These results demonstrate the robustness and scalability of the proposed semantic similarity and relatedness measure, significantly improving existing similarity measures.

Transfer fine-tuning of BERT with phrasal paraphrases

Sentence pair modelling is defined as the task of identifying the semantic interaction between a sentence pair, i.e., paraphrase and textual entailment identification and semantic similarity measurement. It constitutes a set of crucial tasks for research in the area of natural language understanding. Sentence representation learning is a fundamental technology for sentence pair modelling, where the development of the BERT model realised a breakthrough. We have recently proposed transfer fine-tuning using phrasal paraphrases to allow BERT’s representations to be suitable for semantic equivalence assessment between sentences while maintaining the model size. Herein, we reveal that transfer fine-tuning with simplified feature generation allows us to generate representations that are widely effective across different types of sentence pair modelling tasks. Detailed analysis confirms that our transfer fine-tuning helps the BERT model converge more quickly with a smaller corpus for fine-tuning.

Corrigendum to: Similarity of Sentences With Contradiction Using Semantic Similarity Measures

Corrigendum to: Similarity of Sentences With Contradiction Using Semantic Similarity Measures

Semantic similarity and machine learning with ontologies.

Ontologies have long been employed in the life sciences to formally represent and reason over domain knowledge and they are employed in almost every major biological database. Recently, ontologies are increasingly being used to provide background knowledge in similarity-based analysis and machine learning models. The methods employed to combine ontologies and machine learning are still novel and actively being developed. We provide an overview over the methods that use ontologies to compute similarity and incorporate them in machine learning methods; in particular, we outline how semantic similarity measures and ontology embeddings can exploit the background knowledge in ontologies and how ontologies can provide constraints that improve machine learning models. The methods and experiments we describe are available as a set of executable notebooks, and we also provide a set of slides and additional resources at https://github.com/bio-ontology-research-group/machine-learning-with-ontologies.

Mining information from sentences through Semantic Web data and Information Extraction tasks

The Semantic Web provides guidelines for the representation of information about real-world objects (entities) and their relations (properties). This is helpful for the dissemination and consumption of information by people and applications. However, the information is mainly contained within natural language sentences, which do not have a structure or linguistic descriptions ready to be directly processed by computers. Thus, the challenge is to identify and extract the elements of information that can be represented. Hence, this article presents a strategy to extract information from sentences and its representation with Semantic Web standards. Our strategy involves Information Extraction tasks and a hybrid semantic similarity measure to get entities and relations that are later associated with individuals and properties from a Knowledge Base to create RDF triples (Subject–Predicate–Object structures). The experiments demonstrate the feasibility of our method and that it outperforms the accuracy provided by a pattern-based method from the literature.

Phenotype-genotype comorbidity analysis of patients with rare disorders provides insight into their pathological and molecular bases.

Genetic and molecular analysis of rare disease is made difficult by the small numbers of affected patients. Phenotypic comorbidity analysis can help rectify this by combining information from individuals with similar phenotypes and looking for overlap in terms of shared genes and underlying functional systems. However, few studies have combined comorbidity analysis with genomic data. We present a computational approach that connects patient phenotypes based on phenotypic co-occurence and uses genomic information related to the patient mutations to assign genes to the phenotypes, which are used to detect enriched functional systems. These phenotypes are clustered using network analysis to obtain functionally coherent phenotype clusters. We applied the approach to the DECIPHER database, containing phenotypic and genomic information for thousands of patients with heterogeneous rare disorders and copy number variants. Validity was demonstrated through overlap with known diseases, co-mention within the biomedical literature, semantic similarity measures, and patient cluster membership. These connected pairs formed multiple phenotype clusters, showing functional coherence, and mapped to genes and systems involved in similar pathological processes. Examples include claudin genes from the 22q11 genomic region associated with a cluster of phenotypes related to DiGeorge syndrome and genes related to the GO term anterior/posterior pattern specification associated with abnormal development. The clusters generated can help with the diagnosis of rare diseases, by suggesting additional phenotypes for a given patient and potential underlying functional systems. Other tools to find causal genes based on phenotype were also investigated. The approach has been implemented as a workflow, named PhenCo, which can be adapted to any set of patients for which phenomic and genomic data is available. Full details of the analysis, including the clusters formed, their constituent functional systems and underlying genes are given. Code to implement the workflow is available from GitHub.

A large reproducible benchmark of ontology-based methods and word embeddings for word similarity

This work is a companion reproducibility paper of the experiments and results reported in Lastra-Diaz et al. (2019a), which is based on the evaluation of a companion reproducibility dataset with the HESML V1R4 library and the long-term reproducibility tool called Reprozip. Human similarity and relatedness judgements between concepts underlie most of cognitive capabilities, such as categorization, memory, decision-making and reasoning. For this reason, the research on methods for the estimation of the degree of similarity and relatedness between words and concepts has received a lot of attention in the fields of artificial intelligence and cognitive sciences. However, despite the huge research effort done, there is a lack of a self-contained, reproducible and extensible collection of benchmarks which being amenable to become a de facto standard for large scale experimentation in this line of research. In order to bridge this reproducibility gap, this work introduces a set of reproducible experiments on word similarity and relatedness by providing a detailed reproducibility protocol together with a set of software tools and a self-contained reproducibility dataset, which allow that all experiments and results in our aforementioned work to be reproduced exactly. Our aforementioned primary work introduces the largest, most detailed and reproducible experimental survey on word similarity and relatedness reported in the literature, which is based on the implementation of all evaluated methods into the same software platform. Our reproducible experiments evaluate most of methods in the families of ontology-based semantic similarity measures and word embedding models. We also detail how to extend our experiments to evaluate other unconsidered experimental setups. Finally, we provide a corrigendum for a mismatch in the MC28 similarity scores used in our original experiments.

Reading development at the text level: an investigation of surprisal and embeddingbased text similarity effects on eyemovements in Chinese early readers.

This paper describes the use of semantic similarity measures based on distributed representations of words, sentences, and paragraphs (so-called “embeddings”) to assess the impact of supra-lexical factors on eye-movement data from early readers of Chinese. In addition, we used a corpus-based measure of surprisal to assess the impact of local word predictability. Eye movement data from 56 Chinese students were collected (a) in the students’ 4th grade and (b) one year later while they were in 5th grade. Results indicated that surprisal and some text similarity measures have a significant impact on the momentto- moment processing of words in reading. The paper presents an easy-to-use set of tools for linking the low-level aspects of fixation durations to a hierarchy of sentence-level and paragraph-level features that can be computed automatically. The study is the first attempt, as far as we are aware, to track the developmental trajectory of these influences in developing readers across a range of reading abilities. The similarity-based measures described here can be used (a) to provide a measure of reader sensitivity to sentence and paragraph cohesion and (b) to assess specific texts for their suitability for readers of different reading ability levels.

Improving biterm topic model with word embeddings

As one of the fundamental information extraction methods, topic model has been widely used in text clustering, information recommendation and other text analysis tasks. Conventional topic models mainly utilize word co-occurrence information in texts for topic inference. However, it is usually hard to extract a group of words that are semantically coherent and have competent representation ability when the models applied into short texts. It is because the feature space of the short texts is too sparse to provide enough co-occurrence information for topic inference. The continuous development of word embeddings brings new representation of words and more effective measurement of word semantic similarity from concept perspective. In this study, we first mine word co-occurrence patterns (i.e., biterms) from short text corpus and then calculate biterm frequency and semantic similarity between its two words. The result shows that a biterm with higher frequency or semantic similarity usually has more similar words in the corpus. Based on the result, we develop a novel probabilistic topic model, named Noise Biterm Topic Model with Word Embeddings (NBTMWE). NBTMWE extends the Biterm Topic Model (BTM) by introducing a noise topic with prior knowledge of frequency and semantic similarity of biterm. NBTMWE shows the following advantages compared with BTM: (1) It can distinguish meaningful latent topics from a noise topic which consists of some common-used words that appear in many texts of the dataset; (2) It can promote a biterm’s semantically related words to the same topic during the sampling process via generalized $P\acute {o}lya$ Urn (GPU) model. Using auxiliary word embeddings trained from a large scale of corpus, we report the results testing on two short text datasets (i.e., Sina Weibo and Web Snippets). Quantitatively, NBTMWE outperforms the state-of-the-art models in terms of coherence, topic word similarity and classification accuracy. Qualitatively, each of the topics generated by NBTMWE contains more semantically similar words and shows superior intelligibility.

Similarity of Sentences With Contradiction Using Semantic Similarity Measures

Abstract Short text or sentence similarity is crucial in various natural language processing activities. Traditional measures for sentence similarity consider word order, semantic features and role annotations of text to derive the similarity. These measures do not suit short texts or sentences with negation. Hence, this paper proposes an approach to determine the semantic similarity of sentences and also presents an algorithm to handle negation. In sentence similarity, word pair similarity plays a significant role. Hence, this paper also discusses the similarity between word pairs. Existing semantic similarity measures do not handle antonyms accurately. Hence, this paper proposes an algorithm to handle antonyms. This paper also presents an antonym dataset with 111-word pairs and corresponding expert ratings. The existing semantic similarity measures are tested on the dataset. The results of the correlation proved that the expert ratings are in order with the correlation obtained from the semantic similarity measures. The sentence similarity is handled by proposing two algorithms. The first algorithm deals with the typical sentences, and the second algorithm deals with contradiction in the sentences. SICK dataset, which has sentences with negation, is considered for handling the sentence similarity. The algorithm helped in improving the results of sentence similarity.

IWD towards Semantic similarity measure in ontology

Ontology plays a key role in semantic web to represent various concepts and their relations to make knowledge machine understandable. In order to provide a knowledge sharing environment, concept mapping in ontologies is required. In this regard, semantic similarity in the field of information retrieval is quite significant which refers to relatedness in ontology concepts. This semantic similarity may be computed in several ways. In this paper, a new method, based on optimization algorithm, IWD (Intelligent Water Drop), is proposed to computer similarity in ontology concepts. It is used to measure weighted path in concepts of ontology which is further used to find the semantic distance. Semantic similarity is computed on the basis of this semantic distance. Further, with the aid of a case study, a comparative analysis has been presented for the proposed method and other existing similarity methods for semantic similarity.

Impact of low-confidence interactions on computational identification of protein complexes.

Protein complexes are the cornerstones of most of the biological processes. Identifying protein complexes is crucial in understanding the principles of cellular organization with several important applications, including in disease diagnosis. Several computational techniques have been developed to identify protein complexes from protein-protein interaction (PPI) data (equivalently, from PPI networks). These PPI data have a significant amount of false positives, which is a bottleneck in identifying protein complexes correctly. Gene ontology (GO)-based semantic similarity measures can be used to assign a confidence score to PPIs. Consequently, low-confidence PPIs are highly likely to be false positives. In this paper, we systematically study the impact of low-confidence PPIs on the performance of complex detection methods using GO-based semantic similarity measures. We consider five state-of-the-art complex detection algorithms and nine GO-based similarity measures in the evaluation. We find that each complex detection algorithm significantly improves its performance after the filtration of low-similarity scored PPIs. It is also observed that the percentage improvement and the filtration percentage (of low-confidence PPIs) are highly correlated.

Structural and Semantic Similarity Measurement of UML Use Case Diagram

Reusing software has several benefits ranging from reducing cost and risk, accelerating development, and its primary purposes are improving software quality. In the early stage of software development, reusing existing software artifacts may increase the benefit of reusing software because it uses mature artifacts from previous artifacts. One of software artifacts is diagram, and in order to assist the reusing diagram is to find the level of similarity of diagrams. This paper proposes a method for measuring the similarity of the use case diagram using structural and semantic aspects. For structural similarity measurement, Graph Edit Distance is used by transforming each factor and use case into a graph, while for semantic similarity measurement, WordNet, WuPalmer,and Levenshtein were used. The experimentation was conducted on ten datasets from variousprojects. The results of the method were compared with the results of assessments from experts.The measurement of agreement between experts and method was done by using Gwet’s AC1 andPearson correlation coefficient. Measurement results with Gwet’s AC1 diagram similarity are 0,60,which were categorized as “moderate" agreement and the result of measurement with Pearsonis 0.506 which means there is a significant correlation between experts and methods. The resultshowed that the proposed method can be used to find the similarity of the diagram, so finding andreuse of the diagram as a software component can be optimized.