Measuring the short text similarity based on semantic and syntactic information

Yang, Jiaqi; Li, Yongjun; Gao, Congjie; Zhang, Yinyin

doi:10.1016/j.future.2020.07.043

Cited by 38 publications

(10 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The principle of distributional hypothesis is applied in semantic similarity. It means the similar words occurred together and frequently are expected to appear in similar contexts [53]. In earlier studies of semantic similarity, LDA, LSA, NGD, and vector are among the most popular method to compute semantic similarity [22], [43], [46].…”

Section: ) Semantic-similarity Methodsmentioning

confidence: 99%

Revisiting the challenges and surveys in text similarity matching and detection methods

2022

View full text Add to dashboard Cite

The massive amount of information from the internet has revolutionized the field of natural language processing. One of the challenges was estimating the similarity between texts. This has been an open research problem although various studies have proposed new methods over the years. This paper surveyed and traced the primary studies in the field of text similarity. The aim was to give a broad overview of existing issues, applications, and methods of text similarity research. This paper identified four issues and several applications of text similarity matching. It classified current studies based on intrinsic, extrinsic, and hybrid approaches. Then, we identified the methods and classified them into lexical-similarity, syntactic-similarity, semanticsimilarity, structural-similarity, and hybrid. Furthermore, this study also analyzed and discussed method improvement, current limitations, and open challenges on this topic for future research directions. As the results, this paper highlighted the importance of selecting the appropriate preprocessing algorithms to reduce data dimensionality and also combining several algorithms to enhance the overall matching and detection process.

show abstract

Section: ) Semantic-similarity Methodsmentioning

confidence: 99%

Revisiting the challenges and surveys in text similarity matching and detection methods

2022

View full text Add to dashboard Cite

show abstract

“…Zhu et al used neural network feature extraction to group actions and match multiple cells under columns with keywords or phrases [12]. Yang et al proposed a short text similarity calculation method based on semantic and syntactic information, using knowledge and corpus to express different semantics of words, and using a structure analysis tree to capture the syntactic structure of short texts [13]. Munir et al used an adaptive convolution based on syntactic information input to generate lters and then networks, thereby widening the gap between syntactic aware and agnostic SRL systems [14].…”

Section: Related Workmentioning

confidence: 99%

A dynamic domain ontology model based on the optimal matching method of network news

Chen

Zhu

2022

Preprint

View full text Add to dashboard Cite

The method of constructing domain ontology (DO) models is one of the hot issues in ontology research. At present, researchers have conducted in-depth research on the theory and application of ontology construction from their own research fields and obtained abundant research results. However, it is still a puzzle to construct DO models by mining semantic information in web news. Based on the analysis of network news data, this paper proposed a dynamic DO model based on the concept of semantic information optimization and matching and designs an ontology structure updating algorithm according to the relationship between semantic triple concept and pattern to ensure the ability of ontology to keep learning new data structures. Experiments showed that the coverage rate of the ontology model exceeded 70% when processing news data, and it can extract different semantic information of a certain topic news fact, proving the effectiveness of semi-automatic construction of network news DO.

show abstract

“…[11] reviewed existing approaches to measuring semantic similarity at either the document, sentence, or word level, focusing on Arabic text. The approach utilized by [1], [12] employs a set of extracted features based on lexical, syntactic, and semantic computations to detect the similarity between tweet pairs. One approach uses knowledge and corpora to express the meanings of terms to solve the issue of polysemy and includes a constituency parse tree to capture the syntactic structures of short texts.…”

Section: Related Workmentioning

confidence: 99%

NGram Approach for Semantic Similarity on Arabic Short Text

Al-Mahmoud¹,

Sharieh²

2022

IJACSA

View full text Add to dashboard Cite

Measuring the semantic similarity between words requires a method that can simulate human thought. The use of computers to quantify and compare semantic similarities has become an important research area in various fields, including artificial intelligence, knowledge management, information retrieval, and natural language processing. Computational semantics require efficient measures for computing concept similarity, which still need to be developed. Several computational measures quantify semantic similarity based on knowledge resources such as the WordNet taxonomy. Several measures based on taxonomical parameters have been applied to optimize the expression for content semantics. This paper presents a new similarity measure for quantifying the semantic similarity between concepts, words, sentences, short text, and long text based on NGram features and Synonyms of NGram related to the same domain. The proposed algorithm was tested on 700 tweets, and the semantic similarity values were compared with cosine similarity on the same dataset. The results were analyzed manually by a domain expert who concluded that the values provided by the proposed algorithm were better than the cosine similarity values within the selected domain regarding the semantic similarity between the datasets' short texts.

show abstract

Measuring the short text similarity based on semantic and syntactic information

Cited by 38 publications

References 16 publications

Revisiting the challenges and surveys in text similarity matching and detection methods

Revisiting the challenges and surveys in text similarity matching and detection methods

A dynamic domain ontology model based on the optimal matching method of network news

NGram Approach for Semantic Similarity on Arabic Short Text

Contact Info

Product

Resources

About