State-of-the Art: Short Text Semantic Similarity (STSS) Techniques in Question Answering Systems (QAS)

Amur, Zaira Hassan; Hooi, Yewkwang; Sodhar, Irum Naz; Bhanbhro, Hina; Dahri, Kamran

doi:10.1007/978-981-16-2183-3_98

Cited by 5 publications

(11 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, the studies [82][83][84][85][86] suggest using convolutional layers with the ELMO model to improve its performance for extracting text features. These layers used maxpooling to represent the fixed length of the entire word.…”

Section: Elmo Model For Contextual Word Embeddings (Cwe)mentioning

confidence: 99%

See 1 more Smart Citation

Short-Text Semantic Similarity (STSS): Techniques, Challenges and Future Perspectives

et al. 2023

Self Cite

View full text Add to dashboard Cite

In natural language processing, short-text semantic similarity (STSS) is a very prominent field. It has a significant impact on a broad range of applications, such as question–answering systems, information retrieval, entity recognition, text analytics, sentiment classification, and so on. Despite their widespread use, many traditional machine learning techniques are incapable of identifying the semantics of short text. Traditional methods are based on ontologies, knowledge graphs, and corpus-based methods. The performance of these methods is influenced by the manually defined rules. Applying such measures is still difficult, since it poses various semantic challenges. In the existing literature, the most recent advances in short-text semantic similarity (STSS) research are not included. This study presents the systematic literature review (SLR) with the aim to (i) explain short sentence barriers in semantic similarity, (ii) identify the most appropriate standard deep learning techniques for the semantics of a short text, (iii) classify the language models that produce high-level contextual semantic information, (iv) determine appropriate datasets that are only intended for short text, and (v) highlight research challenges and proposed future improvements. To the best of our knowledge, we have provided an in-depth, comprehensive, and systematic review of short text semantic similarity trends, which will assist the researchers to reuse and enhance the semantic information.

show abstract

Section: Elmo Model For Contextual Word Embeddings (Cwe)mentioning

confidence: 99%

“…Moreover, open-ended questions expect answers in open thoughts [19]. There is no specific answer limit for such types of questions, which makes it more challenging for the deep learning models to identify the correct or relevant answers [29,82].…”

Section: Performance Measurements Of Bert Elmo and Gpt-2mentioning

confidence: 99%

Short-Text Semantic Similarity (STSS): Techniques, Challenges and Future Perspectives

et al. 2023

Self Cite

View full text Add to dashboard Cite

show abstract

“…It has a high rate of ambiguity due to similar patterns and vowel deletions. Morphological analysis has an impact on higher levels of semantic (11) and syntactic analysis. Although they are recognized as part of great languages, the variety of affixes in Sindhi makes it more complex.…”

Section: Sindhi Morphologymentioning

confidence: 99%

“…The branch of morphology known as morpheme studies morphemes, the smallest meaningful grammatical unit. Bound morphemes are unable to stand on their own and can only have significance when they are a part of a word (11) . Combining different morphemes, such as particular and uplifting morphemes, can give a phrase meaning.…”

Section: Bound Morphemementioning

confidence: 99%

See 1 more Smart Citation

Morphology-Assisted Sindhi Text Analysis for Natural Language Processing Applications

Sodhar,

Buller,

Sulaiman

2023

IJST

View full text Add to dashboard Cite

Objectives: Understanding word construction and internal structure, especially in the Sindhi language, requires knowledge of the linguistic field known as morphology. In this study, Sindhi morphology is examined with particular attention paid to its structure, function, nature, word categories, and writing system. Natural Language Processing (NLP) relies on morphological analysis to identify words and their grammatical features, enabling applications like spell checkers and machine translation. A comparative analysis is done to comprehend how Sindhi Morphology developed. Because research on morphology analysis lack proper classification and cover both modern and conventional methodologies, Sindhi morphology variances present difficulties for computerization. Methods: Morphological analysis is crucial in Natural Language Processing (NLP) domains like spell checkers and gadget translation, studying word production and phrase shape using morphemes, the smallest grammatical elements in a language. Morphemes are the building blocks of words and are divided into free and fixed morphemes. Findings: Sindhi's rich morphology and complexity enable borrowing and lending of words, but ambiguity is high due to similar patterns and vowel deletions. Morphological analysis influences semantic and syntactic analysis. Computerization is challenging due to prefixes, suffixes, and stem positions. Primary and secondary words can be subdivided into compound and complicated terms. The language uses initial, middle, and end writing styles. Novelty: This research aims to develop an automatic Sindhi morphological analyzer for future NLP applications, ensuring compatibility with existing Information Technology world applications. It will help understand Sindhi word structure and benefit software developers in developing Sindhi natural language and speech processing applications.

show abstract

Symbol Detection in a Multi-class Dataset Based on Single Line Diagrams using Deep Learning Models

Bhanbhro,

Hooi,

Kusakunniran

et al. 2023

IJACSA

View full text Add to dashboard Cite

Single Line Diagrams (SLDs) are used in electrical power distribution systems. These diagrams are crucial to engineers during the installation, maintenance, and inspection phases. For the digital interpretation of these documents, deep learning-based object detection methods can be utilized. However, there is a lack of efforts made to digitize the SLDs using deep learning methods, which is due to the class-imbalance problem of these technical drawings. In this paper, a method to address this challenge is proposed. First, we use the latest variant of You Look Only Once (YOLO), YOLO v8 to localize and detect the symbols present in the single-line diagrams. Our experiments determine that the accuracy of symbol detection based on YOLO v8 is almost 95%, which is more satisfactory than its previous versions. Secondly, we use a synthetic dataset generated using multi-fake class generative adversarial network (MFCGAN) and create fake classes to cope with the class imbalance problem. The images generated using the GAN are then combined with the original images to create an augmented dataset, and YOLO v5 is used for the classification of the augmented dataset. The experiments reveal that the GAN model had the capability to learn properly from a small number of complex diagrams. The detection results show that the accuracy of YOLO v5 is more than 96.3%, which is higher than the YOLO v8 accuracy. After analyzing the experiment results, we might deduce that creating multiple fake classes improved the classification of engineering symbols in SLDs.

show abstract

State-of-the Art: Short Text Semantic Similarity (STSS) Techniques in Question Answering Systems (QAS)

Cited by 5 publications

References 26 publications

Short-Text Semantic Similarity (STSS): Techniques, Challenges and Future Perspectives

Short-Text Semantic Similarity (STSS): Techniques, Challenges and Future Perspectives

Morphology-Assisted Sindhi Text Analysis for Natural Language Processing Applications

Symbol Detection in a Multi-class Dataset Based on Single Line Diagrams using Deep Learning Models

Contact Info

Product

Resources

About