[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125712-en":3,"doc-seo-125712-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},125712,16904993612988,"Olivia Brown","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",6,"Technology","Machine Learning Model for Automated Assessment of Short Subjective Answers","Natural Language Processing (NLP) applies semantic similarity to tasks such as information retrieval, question-answering, and sentiment analysis, with a strong role in personalized learning through assessment and adaptive tests. Open-ended questions are common, yet their value depends on understanding the meaning of short student answers, which are difficult to analyze due to limited length, low clarity, and weak structure. This work presents a BERT-based transformer model using multi-head attention to identify and assess short subjective answers, improving assessment performance and outperforming prior techniques.","Machine Learning Model for Automated Assessment  \nof Short Subjective Answers  \nZaira Hassan Amur 1, Yew Kwang Hooi2, Hina Bhanbro3, Mairaj Nabi Bhatti4, Gul Muhammad Soomro5  \nDept. Computer and Information Sciences, Universiti Teknologi PETRONAS, Perak, Malaysia1, 2, 3 Dept. Information Technology, Shaheed Benazir Bhuto University, Nawabshah, Pakistan4 Dept. Information Technology, Tomas Bata University, Zlin, Czech Republic5  \nAbstract—Natural Language Processing (NLP) has recently gained significant attention; where, semantic similarity techniques are widely used in diverse applications, such as information retrieval, question-answering systems, and sentiment analysis. One promising area where NLP is being applied, is personalized learning, where assessment and adaptive tests are used to capture students' cognitive abilities. In this context, openended questions are commonly used in assessments due to their simplicity, but their effectiveness depends on the type of answer expected. To improve comprehension, it is essential to understand the underlying meaning of short text answers, which is challenging due to their length, lack of clarity, and structure. Researchers have proposed various approaches, including distributed semantics and vector space models, However, assessing short answers using these methods presents significant challenges, but machine learning methods, such as transformer models with multi-head attention, have emerged as advanced techniques for understanding and assessing the underlying meaning of answers. This paper proposes a transformer learning model that utilizes multi-head attention to identify and assess students' short answers to overcome these issues. Our approach improves the performance of assessing the assessments and outperforms current state-of-the-art techniques. We believe our model has the potential to revolutionize personalized learning and significantly contribute to improving student outcomes.  \nKeywords—Natural language processing; short text; answer assessment; BERT; semantic similarity  \nI. INTRODUCTION  \nSemantic similarity is a technique used to determine whether two separate texts have the same meaning. It is a crucial task in natural language processing (NLP) and can be applied to a range of downstream applications, such as text classification, summarization, and question-answering systems (QAS) . In the early days of text similarity research, the emphasis was often on comparing lengthy texts, such as news articles, large corpora, and documents. Compared to lengthy writings, short texts have unique characteristics that pose challenges to traditional approaches for measuring similarity. First, short texts have a shorter form, which means that traditional approaches such as knowledge-based, and corpusbased which rely on examining common terms in two texts to determine similarity often lack statistical evidence to support them [1] . Second, short writings frequently use colloquial language and contain numerous typographical and grammatical errors. Third, due to the huge volume of short messages produced, they tend to be ambiguous and noisy [2] . Consequently, it is difficult to use traditional text similarity  \nmethods for short texts. There are three main methods for calculating the similarity of short texts. The first method is word-level semantic-based, which looks at the words in the texts and finds pairs of similar words. It then calculates the similarity of the whole text based on the similarity of these word pairs. The second method is semantic modeling-based, which looks at the overall structure of the texts and compares the two models to see how similar they are. The third method is deep learning-based, which converts the short texts into \"word embeddings\" and calculates how close the words are to eachother using cosine similarity [3] . Other approaches such as convolutional neural networks (CNN) and recurrent neural networks (RNN) can take a long time to train due to their","cbCaib4CvlZxjWB5","https://ap.wps.com/l/cbCaib4CvlZxjWB5","pdf",928983,1,9,"English","en",105,"# Introduction\n## Semantic similarity and short-text challenges\n## Similarity calculation methods\n## Deep learning and transformer-based approaches\n## Student assessment with multi-head attention transformers","[{\"question\":\"Why is assessing semantic similarity harder for short subjective answers than for long texts?\",\"answer\":\"Short texts have less statistical evidence for term overlap methods, often use colloquial language with typos and grammar errors, and are noisy and ambiguous due to their volume.\"},{\"question\":\"What similarity approaches are discussed for short texts?\",\"answer\":\"The document outlines word-level semantic methods, semantic modeling-based methods, and deep learning methods that use word embeddings with cosine similarity, along with alternatives like CNN and RNN.\"},{\"question\":\"How does the proposed method assess short subjective answers?\",\"answer\":\"It uses a BERT language model with a transformer architecture and multi-head attention to capture word importance and determine the meaning of students’ short answers for assessment.\"}]","Machine Learning Model for Automated Assessment of Short Subjective Answers | PDF",1785900782,23,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"machine-learning-model-for-automated-assessment-of-short-subjective-answers","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/technology/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/machine-learning-model-for-automated-assessment-of-short-subjective-answers/125712/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is assessing semantic similarity harder for short subjective answers than for long texts?","Question",{"text":75,"@type":76},"Short texts have less statistical evidence for term overlap methods, often use colloquial language with typos and grammar errors, and are noisy and ambiguous due to their volume.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What similarity approaches are discussed for short texts?",{"text":80,"@type":76},"The document outlines word-level semantic methods, semantic modeling-based methods, and deep learning methods that use word embeddings with cosine similarity, along with alternatives like CNN and RNN.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the proposed method assess short subjective answers?",{"text":84,"@type":76},"It uses a BERT language model with a transformer architecture and multi-head attention to capture word importance and determine the meaning of students’ short answers for assessment.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,113,118,123,127,130,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":111,"slug":112},50,"technology",{"id":114,"doc_module":4,"doc_module_name":46,"category_name":115,"show_sort_weight":116,"slug":117},7,"Healthcare",40,"healthcare",{"id":119,"doc_module":4,"doc_module_name":46,"category_name":120,"show_sort_weight":121,"slug":122},8,"Research & Report",30,"research-report",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]