Short text similarity measurement methods: a review

Abstract

Short text similarity measurement methods play an important role in many applications within natural language processing. This paper reviews the research literature on short text similarity (STS) measurement method with the aim to (i) classify and give a broad overview of existing techniques; (ii) find out its strengths and weaknesses in terms of the domain the independence, language independence, requirement of semantic knowledge, corpus and training data, ability to identify semantic meaning, word order similarity and polysemy; and (iii) identify semantic knowledge and corpus resource that can be utilized for the STS measurement methods. Furthermore, our study also considers various issues such as the difference between the various text similarity methods and the difference between semantic knowledge sources and corpora for text similarity. Although there are a few review papers in this area, they focus mostly only on one/two existing techniques. Furthermore, existing review papers do not cover recent research. To the best of our knowledge, this is a comprehensive systematic literature review on this topic. The findings of this research can be as follows: It identified four semantic knowledge and eight corpus resources as external resources that can be classified into general-purpose and domain-specific. Furthermore, the existing techniques can be classified into string-based, corpus-based, knowledge-based and hybrid-based. Moreover, expert researchers can utilize this review as a benchmark as well as reference to the limitations of current techniques. The paper also identifies the open issues that can be considered as feasible opportunities for future research directions.Keywords Natural language processing Á Text mining Á Linguistics Á Similarity measures Á Semantics Á Syntax Communicated by V. Loia.

A Novel Approach for Tweet Similarity in a Context-Aware Fake News Detection Model

“…Several methods to compare documents include word-based, keyword-based, n-gram-based, and Latent Semantic Analysis-based methodologies (see [16]). [17], on their review specifically about short text similarity (STS) tasks, broadens this classification to a more generic overview, to which he classifies the tasks as string-based, corpus-based, knowledge-based, and hybrid-based. Our work will use a hybrid approach (corpus-based and string-based), using the work of [14] as a reference method.…”

Bullshit, Pragmatic Deception, and Natural Language Processing

“…A number of NLP methods, e.g. adapted from various text similarity measures, can then be employed to compare the reconstructed QUDs to the overt question to see whether and where they overlap (Croft et al, 2013;Prasetya et al, 2018;Prakoso et al, 2021). Evasive bullshitting by way of introducing novel QUDs (and pretending they answer the original one) occurs when the topic of question and answer matches, but the implicit QUDs differ strongly from the overt ones.…”

Automatic grading for Arabic short answer questions using optimized deep learning model

“…So, NLP is based on textual similarity evaluation. [ 1 ] showed and discussed the popular methods used in evaluating short text similarity, such that they examined and compared each other and demonstrated how the approaches used in short text similarity evaluation changed over time. While some researchers, such as the work of [ 2 ], used several words overlapping methods to count the similar words between the learner’s answer and the model answer, this study concluded that the algorithm of the overlapping word cannot overcome the semantic similarity problems, such as some students can express the correct answer in words different than the model answer keywords.…”