Answering System Research Articles

Intelligent maritime question-answering and recommendation system based on maritime vessel activity knowledge graph

Traditional maritime traffic management typically relies on positioning data for data mining without incorporating other multi-source data to analyze the maritime vessel activity, which cannot conduct comprehensive maritime knowledge mining. Thus, this study integrates multi-source data, such as trajectory, maritime accident text, and geographic data, to create a maritime vessel activity knowledge graph. On this basis, a question-answering model is developed based on a bidirectional question-answering attention graph neural network, and a personalized recommendation model is developed based on an attention-enhanced joint knowledge propagation and a user preference graph neural network. The former assists users in extracting valuable information from the maritime vessel activity knowledge graph, while the latter predicts the users' potential interests and automatically recommends vessel entities based on their historical query information. Experimental results show that the proposed question-answering model improved the F1-score by 2.31%–10.09% compared to state-of-the-art baseline models on the MVA question-answering dataset. Similarly, the proposed personalized recommendation model improved the click-through rate prediction accuracy by 2.46%–7.05% compared to state-of-the-art baseline models on the MVA personalized recommendation dataset.

Design and Implementation of an Interactive Question-Answering System with Retrieval-Augmented Generation for Personalized Databases

This study introduces a novel approach to personalized information retrieval by integrating retrieval augmentation generation (RAG) with a personalized database system. Recent advancements in large language models (LLMs) have shown impressive text generation capabilities but face limitations in knowledge accuracy and hallucinations. Our research addresses these challenges by combining LLMs with structured, personalized data to enhance search precision and relevance. By tagging keywords within personal documents and organizing information into context-based categories, users can conduct efficient searches within their data repositories. We conducted experiments using the GPT-3.5 and text-embedding-ada-002 models and evaluated the RAG assessment framework with five different language models and two embedding models. Our results indicate that the combination of GPT-3.5 and text-embedding-ada-002 is effective for a personalized database question-answering system, with potential for various language models depending on the application. Our approach offers improved accuracy, real-time data updates, and enhanced user experience, making a significant contribution to information retrieval by LLMs and impacting various artificial intelligence applications.

TourMapQA: using deep learning to develop a vietnam map-based tourism question answering system

<p>A question answering system is an important task in information retrieval. In recent years, this system has been interested in research and achieved outstanding results. In general, the output of the question answering is text. However, few studies have used a map as an answer to the question answering in Vietnam tourism. This paper introduces a question answering system integrating long short-term memory (LSTM) on the Vietnam map. Specifically, our model received an input question about any road in Vietnam. Then, the model used LSTM to indicate the coordinate of that road and called the Dijkstra algorithm to find the shortest path from the current location to the input road. Next, from the coordinate of the input road, we leveraged the LSTM model to identify sightseeing places that were on the shortest path. Finally, our system showed all the sightseeing places on the Vietnam map. Technically, the experimental results showed that our model’s performance was improved than previous models such as recurrent neural network, recurrent neural network with embedding, bidirectional recurrent neural network, and encoder-decoder recurrent neural network. Practically in terms, we applied our method to build a real application and compared it with Google Maps, and Bing Map.</p>

Strong Solutions of the Neuronal Responses System

We explore a connected reaction-diffusion system involving neural responses within limited convex open domains . Utilizing the Classical Faedo-Galerkin technique and employing compactness arguments, we establish the existence, uniqueness, and continuous dependence on initial data for strong solutions.

F-KGQA: A fuzzy question answering system for knowledge graphs

The wide usage of large-scale knowledge graphs (KGs) motivates the development of user-friendly interfaces so that knowledge graphs become more readily accessible to a larger population. Natural language-based question answering (QA) systems are widely investigated and developed in the context of KGs, which can provide users with a natural means to retrieve the information they need from KGs without expecting them to know the query language. It is very common that natural language contains linguistic terms (fuzzy terms), and fuzzy (flexible) query has been widely investigated in the context of databases. This paper contributes a QA system with fuzzy terms over KGs called f-KGQA. f-KGQA can deal with different types of questions, including simple questions, complex questions, and questions with fuzzy terms. More importantly, users are provided with a channel to flexibly define their fuzzy terms based on their understanding. Our experimental results demonstrate the effectiveness and applicability of f-KGQA in handling questions with fuzzy terms.

Application of large language models based on knowledge graphs in question-answering systems: A review

The integration of Knowledge Graphs (KGs) and Large Language Models (LLMs) is emerging as a transformative advancement in AI, particularly within Question Answering (QA) systems. Traditional QA systems, constrained by static knowledge bases, have struggled with multimodal queries and personalized responses. The deep integration of KGs and LLMs offers a novel approach, combining the structured, contextual understanding of KGs with the semantic parsing capabilities of LLMs. This review explores the methodologies, algorithms, datasets, and applications of KG-LLM integration in QA systems, highlighting key research that enhances model performance, reasoning, and domain-specific applications. It addresses technical challenges such as data consistency, semantic understanding, and system optimization. Future directions focus on improving intrinsic model performance and achieving deeper integration of KGs and LLMs. This comprehensive overview underscores the potential of KG-LLM synergy to significantly improve service quality across diverse industries, including education and healthcare.

Combining large language models with enterprise knowledge graphs: a perspective on enhanced natural language understanding.

Knowledge Graphs (KGs) have revolutionized knowledge representation, enabling a graph-structured framework where entities and their interrelations are systematically organized. Since their inception, KGs have significantly enhanced various knowledge-aware applications, including recommendation systems and question-answering systems. Sensigrafo, an enterprise KG developed by Expert.AI, exemplifies this advancement by focusing on Natural Language Understanding through a machine-oriented lexicon representation. Despite the progress, maintaining and enriching KGs remains a challenge, often requiring manual efforts. Recent developments in Large Language Models (LLMs) offer promising solutions for KG enrichment (KGE) by leveraging their ability to understand natural language. In this article, we discuss the state-of-the-art LLM-based techniques for KGE and show the challenges associated with automating and deploying these processes in an industrial setup. We then propose our perspective on overcoming problems associated with data quality and scarcity, economic viability, privacy issues, language evolution, and the need to automate the KGE process while maintaining high accuracy.

Optimizing biomedical information retrieval with a keyword frequency-driven prompt enhancement strategy

BackgroundMining the vast pool of biomedical literature to extract accurate responses and relevant references is challenging due to the domain's interdisciplinary nature, specialized jargon, and continuous evolution. Early natural language processing (NLP) approaches often led to incorrect answers as they failed to comprehend the nuances of natural language. However, transformer models have significantly advanced the field by enabling the creation of large language models (LLMs), enhancing question-answering (QA) tasks. Despite these advances, current LLM-based solutions for specialized domains like biology and biomedicine still struggle to generate up-to-date responses while avoiding “hallucination” or generating plausible but factually incorrect responses.ResultsOur work focuses on enhancing prompts using a retrieval-augmented architecture to guide LLMs in generating meaningful responses for biomedical QA tasks. We evaluated two approaches: one relying on text embedding and vector similarity in a high-dimensional space, and our proposed method, which uses explicit signals in user queries to extract meaningful contexts. For robust evaluation, we tested these methods on 50 specific and challenging questions from diverse biomedical topics, comparing their performance against a baseline model, BM25. Retrieval performance of our method was significantly better than others, achieving a median Precision@10 of 0.95, which indicates the fraction of the top 10 retrieved chunks that are relevant. We used GPT-4, OpenAI's most advanced LLM to maximize the answer quality and manually accessed LLM-generated responses. Our method achieved a median answer quality score of 2.5, surpassing both the baseline model and the text embedding-based approach. We developed a QA bot, WeiseEule (https://github.com/wasimaftab/WeiseEule-LocalHost), which utilizes these methods for comparative analysis and also offers advanced features for review writing and identifying relevant articles for citation.ConclusionsOur findings highlight the importance of prompt enhancement methods that utilize explicit signals in user queries over traditional text embedding-based approaches to improve LLM-generated responses for specialized queries in specialized domains such as biology and biomedicine. By providing users complete control over the information fed into the LLM, our approach addresses some of the major drawbacks of existing web-based chatbots and LLM-based QA systems, including hallucinations and the generation of irrelevant or outdated responses.

BioASQ Synergy: a dialogue between question-answering systems and biomedical experts for promoting COVID-19 research.

This article presents the novel BioASQ Synergy research process which aims to facilitate the interaction between biomedical experts and automated question-answering systems. The proposed research allows systems to provide answers to emerging questions, which in turn are assessed by experts. The assessment of the experts is fed back to the systems, together with new questions. With this iteration, we aim to facilitate the incremental understanding of a developing problem and contribute to solution discovery. The results suggest that the proposed approach can assist researchers to navigate available resources. The experts seem to be very satisfied with the quality of the ideal answers provided by the systems, suggesting that such systems are already useful in answering open research questions. BioASQ Synergy aspires to provide a tool that gives the experts easy and personalized access to the latest findings in a fast-growing corpus of material. In this article, we envisioned BioASQ Synergy as a continuous dialogue between experts and systems to issue open questions. We ran an initial proof-of-concept of the approach, in order to evaluate its usefulness, both from the side of the experts, as well as from the side of the participating systems.

Critique of Reification of Art and Creativity in the Digital Age: A Lukácsian Approach to AI and NFT Art

Abstract This article critically examines the emergent phenomena of AI-generated and NFT art through the lens of Georg Lukács’ theory of reification and its existential implications. Lukács argued that under capitalism, social relations and human experiences are transformed into objective, quantifiable commodities, leading to a fragmented and alienated consciousness. Applying this framework to AI and NFT art, these technologies can be said to represent extreme examples of the reification of art and creativity in the digital age. AI art generators reduce artistic production to abstract, computable properties divorced from lived experience, while NFTs transform digital art into speculative commodities, imposing the logic of private property and exchange value onto the previously open domain of online culture. The existential dimension of this reification is explored, raising questions about the nature of creativity, originality, and the value of art in an increasingly financialized and automated world. The article suggests that a Lukácsian critique must not only diagnose the reified character of these cultural forms but also identify their potential for resistance and transformation, pointing toward a re-humanized and emancipatory vision of art in the digital age. Contemporary theorists such as Tiziana Terranova, Nick Dyer-Witheford, and Benjamin Noys are invoked to further elucidate these issues.

Data or mathematics? Solutions to semantic problems in artificial intelligence

Data support is already driving the development of artificial intelligence. But it cannot solve the semantic problem of artificial intelligence. This requires improving the semantic understanding ability of artificial intelligence. Therefore, a question answering system based on semantic problem processing is proposed in this study. The question answering system utilizes an improved unsupervised method to extract keywords. This technology integrates the semantic feature information of text into traditional word graph model algorithms. On this basis, semantic similarity information is used to calculate and allocate the initial values and edge weights of each node in the PageRank model. And corresponding restart probability matrices and transition probability matrices are constructed for iterative calculation and keyword extraction. Simultaneously, an improved semantic dependency tree was utilized for answer extraction. The improved keyword extraction method shows a decreasing trend in P and R values. The improved answer extraction method has a maximum P-value of 0.876 in the training set and 0.852 in the test set. In a question answering system based on keyword and answer extraction, the improved method has lower loss function values and running time. The improved method has a larger area under ROC. The results of the validation analysis confirm that the improved method in this experiment has high accuracy and robustness when dealing with semantic problems.

Building efficient and effective OpenQA systems for low-resource languages

Question answering (QA) is the task of answering questions posed in natural language with free-form natural language answers extracted from a given passage. In the OpenQA variant, only a question text is given, and the system must retrieve relevant passages from an unstructured knowledge source and use them to provide answers, which is the case in the mainstream QA systems on the Web. QA systems currently are mostly limited to the English language due to the lack of large-scale labeled QA datasets in non-English languages. In this paper, we show that effective, low-cost OpenQA systems can be developed for low-resource contexts. The key ingredients are (1) weak supervision using machine-translated labeled datasets and (2) a relevant unstructured knowledge source in the target language context. Furthermore, we show that only a few hundred gold assessment examples are needed to reliably evaluate these systems. We apply our method to Turkish as a challenging case study, since English and Turkish are typologically very distinct and Turkish has limited resources for QA. We present SQuAD-TR, a machine translation of SQuAD2.0, and we build our OpenQA system by adapting ColBERT-QA and retraining it over Turkish resources and SQuAD-TR using two versions of Wikipedia dumps spanning two years. We obtain a performance improvement of 24–32% in the Exact Match (EM) score and 22–29% in the F1 score compared to the BM25-based and DPR-based baseline QA reader models. Our results show that SQuAD-TR makes OpenQA feasible for Turkish, which we hope encourages researchers to build OpenQA systems in other low-resource languages. We make all the code, models, and the dataset publicly available at https://github.com/boun-tabi/SQuAD-TR.

From text to multimodal: a survey of adversarial example generation in question answering systems

AbstractIntegrating adversarial machine learning with question answering (QA) systems has emerged as a critical area for understanding the vulnerabilities and robustness of these systems. This article aims to review adversarial example-generation techniques in the QA field, including textual and multimodal contexts. We examine the techniques employed through systematic categorization, providing a structured review. Beginning with an overview of traditional QA models, we traverse the adversarial example generation by exploring rule-based perturbations and advanced generative models. We then extend our research to include multimodal QA systems, analyze them across various methods, and examine generative models, seq2seq architectures, and hybrid methodologies. Our research grows to different defense strategies, adversarial datasets, and evaluation metrics and illustrates the literature on adversarial QA. Finally, the paper considers the future landscape of adversarial question generation, highlighting potential research directions that can advance textual and multimodal QA systems in the context of adversarial challenges.

Considering Cost, Creativity, and Convenience in the Creation of an Open Educational Resource

It is easy to become entrenched in our same old patterns as educators. In our physiology classrooms at Johnson County Community College (JCCC), we can even become entrenched with the same old equipment—like our pair of ancient hot plates that continue to survive because they actually do heat faster than the newer ones. However, “newer” sometimes really can be “better”. Open educational resources (OERs) are an example of a newer development that can be better (OER and Low-Cost Materials at Penn State, n.d.; UOW Library, n.d.). They are futuristic versions of academic textbooks present in our students’ reality. Over the past 2 decades, the nitty gritty details of OERs have been taking shape—e.g. licensing, copyrighting, types of resources, and initiatives. OERs truly are for educational purposes; they are teaching materials that exist in the open domain, with no cost for students, and are conveniently available and adaptable for professors. We wanted to join in the current OER movement, so we began to think with small steps. Research strongly supports the use of OERs in classrooms to increase student learning for a variety of reasons (Hilton, 2016). In addition to tangible student benefits, professors can customize their course content with OERs, built on a platform designed for flexibility, creativity, and opportunities for collaboration. The list is long for OER-related advantages that support both the educator and student. In our human physiology laboratory course, we found ourselves considering the creation of an OER laboratory manual with many of these outcomes in mind.

Natural Language Processing Pretraining Language Model for Computer Intelligent Recognition Technology

Computer intelligent recognition technology refers to the use of computer vision, Natural Language Processing (NLP), machine learning and other technologies to enable computers to recognize, analyze, understand and answer human language and behavior. The common applications of computer intelligent recognition technology include image recognition, NLP, face recognition, target tracking, and other fields. NLP is a field of computer science, which involves the interaction between computers and natural languages. NLP technology can be used to process, analyze and generate natural language data, such as text, voice and image. Common NLP technology applications include language translation, emotion analysis, text classification, speech recognition and question answering system. Language model is a machine learning model, which uses a large number of text data for training to learn language patterns and relationships in text data. Although the language model has made great progress in the past few years, it still faces some challenges, including: poor semantic understanding, confusion in multilingual processing, slow language processing and other shortcomings. Therefore, in order to optimize these shortcomings, this article would study the pre-training language model based on NLP technology, which aimed at using NLP technology to optimize and improve the performance of the language model, thus optimizing the computer intelligent recognition technology. The model had a higher language understanding ability and more accurate prediction ability. In addition, the model could learn language rules and structures by using a large number of corpus, so as to better understand natural language. Through experiments, it could be known that the data size and total computing time of the traditional Generative Pretrained Transformer-2 (GPT-2) language model were 10 GB and 97 hours respectively. The data size and total computing time of BERT (Bidirectional Encoder Representations from Transformer) were 12 GB and 86 hours respectively. The data size and total computing time of the pre-training language model based on NLP were 18 GB and 71 hours respectively. Obviously, the pre-training language model based on NLP had a larger data size and shorter computing time. The experimental results showed that the NLP technology could better optimize the language model and effectively improve its various capabilities. This article opened up a new development direction for computer intelligent recognition technology and provided excellent technical support for the development of language models.

Thai Question-Answering System Using Similarity Search and LLM

A question-answering (QA) system is essential to an organization where numerous QA pairs respond to customer queries. Choosing the right pair corresponding to the query is a complex task. Although the QA system from a commercial product like ChatGPT provides an excellent solution, it is costly, and the fine-tuned Large Language Model (LLM) cannot be downloaded for private use at the local site. In addition, the cost of using such LLM may significantly increase when the number of users grows. We propose a Thai QA system that can swiftly respond and correctly match the user query to the reference answer in the QA dataset. The proposed system encodes both QA pairs and a query into individual embeddings and finds a couple of QA pairs that are most related to the query by using the fast similarity search called Faiss (Facebook AI Similarity Search.) Afterward, the relevant QA pairs and the query are fed to the fine-tuned LLM (WangchanBERTa - pretraining multilingual transformer-based) to choose the single best match QA pair. The fine-tuned WangchanBERTa can retrieve the correct answer and respond to the query naturally. The experiment conducted on the Thai Wiki QA dataset indicates the superior ROUGE values, precision, recall, F1-score, and runtime of the proposed system against other strategies.

Comparative Analysis of State-of-the-Art Q A Models: BERT, RoBERTa, DistilBERT, and ALBERT on SQuAD v2 Dataset

In the rapidly evolving landscape of natural language processing (NLP) and artificial intelligence, recent years have witnessed significant advancements, particularly in text-based question-answering (QA) systems. The Stanford Question Answering Dataset (SQuAD v2) has emerged as a prominent benchmark, offering diverse language understanding challenges. This study conducts a thorough examination of cutting-edge QA models—BERT, DistilBERT, RoBERTa, and ALBERT—each featuring distinct architectures, focusing on their training and performance on SQuAD v2. The analysis aims to uncover the unique strengths of each model, providing insights into their capabilities and exploring the impact of different training techniques on their performance. The primary objective is to enhance our understanding of text-based QA systems' evolution and their effectiveness in real-world scenarios. The results of this comparative study are poised to influence the utilization and development of these models in both industry and research. The investigation meticulously evaluates BERT, ALBERT, RoBERTa, and DistilBERT QA models using the SQuAD v2 dataset, emphasizing instances of accurate responses and identifying areas where completeness may be lacking. This nuanced exploration contributes to the ongoing discourse on the advancement of text-based question-answering systems, shedding light on the strengths and limitations of each QA model. Based on the results obtained, ALBERT achieved an exact match of 86.85% and an F1 score of 89.91% on the SQuAD v2 dataset, demonstrating superior performance in both answerable ('HasAns') and unanswerable ('NoAns') questions. BERT and RoBERTa also showed strong performance, while DistilBERT lagged slightly behind. This study provides a significant contribution to the advancement of text-based question-answering systems, offering insights that can shape the utilization of these models in both industry and research domains.

A Question Answering System Application Integrated with Chatbot Using NLP

Objective : A Question Answering System Application integrated with Chatbot using NLP is a platform designed to meet the needs of students, enabling effective communication between students and teachers while encouraging effective problem-solving and interactive knowledge exchange. Methods: The interface provides an optional space for learning inquiry, encouraging students to share their questions and concerns. This user-friendly interface allows students to easily submit questions, which are quickly distributed and reported to the appropriate teacher or expert. Findings: A Question Answering System Application integrated with Chatbot using NLP enables greater engagement and supports learning by providing a framework for resolving education-related questions. Novelty: It promotes effective problem-solving, improves interaction between students and teachers, and ultimately encourages students to take control of their learning. Keywords: Query Chatbot, Natural Language Processing (NLP), Question Answering System Application, Collaborative Learning, Automated Answering System

An Intelligent Hand-Assisted Diagnosis System Based on Information Fusion.

This research proposes an innovative, intelligent hand-assisted diagnostic system aiming to achieve a comprehensive assessment of hand function through information fusion technology. Based on the single-vision algorithm we designed, the system can perceive and analyze the morphology and motion posture of the patient's hands in real time. This visual perception can provide an objective data foundation and capture the continuous changes in the patient's hand movement, thereby providing more detailed information for the assessment and providing a scientific basis for subsequent treatment plans. By introducing medical knowledge graph technology, the system integrates and analyzes medical knowledge information and combines it with a voice question-answering system, allowing patients to communicate and obtain information effectively even with limited hand function. Voice question-answering, as a subjective and convenient interaction method, greatly improves the interactivity and communication efficiency between patients and the system. In conclusion, this system holds immense potential as a highly efficient and accurate hand-assisted assessment tool, delivering enhanced diagnostic services and rehabilitation support for patients.

Question Answering System Based on Bideirectional Long-Short-Term Memory (Bilstm)

In the modern world, Q&A systems are essential for promoting better communication between people and technology. These systems play an important role in collecting information quickly and efficiently, and this leads to great progress in learning, teaching and development in many areas of life. Using deep learning techniques, this research addresses the problem of excellent prediction of the questions that need to be answered. We created a question-and-answer system using "Bidirectional Long Short-Term Memory (BiLSTM)", a modern neural network known for its accuracy and results in text analysis and natural language understanding. This technique is more effective in understanding questions and producing very accurate answers because of its special ability to pay attention to preceding and following information in a sentence. Preprocessing was used to remove unnecessary, unimportant and time-consuming data. The "Stanford Question Answering Dataset version 2 (SQuAD 2.0)"was used, which is considered one of the important datasets used in the field of machine learning and natural language processing. The following evaluation metrics were used to evaluate the model’s performance: “Mean Average Precision(MAP), Mean Reciprocal Rank(MRR), Recall, Precision, Loss, F1 Score, and Exact Match (EM). The results, based on 150 epochs (EPOGs) and 128 batch sizes with a cleaned dataset split into 70% training and 30% test/validation (15% each), are as follows:"Precision (0.966), Loss (0.591), F1-score (0.966), Recall (0.967), EM (0.967), MRR(0.918), MAP (0.776), and accuracy(0.966)". Interestingly, the highest performance was observed when using the accuracy measure.