Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
594
result(s) for
"Question-answering systems"
Sort by:
Research on the construction and application of retrieval enhanced generation (RAG) model based on knowledge graph
Generative pre-trained language models have demonstrated strong capabilities in natural language processing tasks, but they still suffer from “fact hallucination” and weak knowledge timeliness in open-domain question answering and text generation. To improve the accuracy and knowledge consistency of generated content, this paper proposes a Knowledge Graph-based Retrieval Enhanced Generation Model (KG-RAG), which integrates structured knowledge graphs into traditional RAG architectures to enhance the model’s ability to understand semantic and inferential relationships. The model designs a dual-channel retrieval mechanism: on one hand, it uses Dense Passage Retrieval (DPR) for vectorized retrieval of unstructured texts; on the other hand, it employs graph neural networks (GNN) to structurally retrieve semantic paths within the knowledge graph, and through path attention mechanisms, it filters out the most relevant entity relationship chains to guide the knowledge injection module. Experimental results on the Natural Questions and PubMedQA datasets show that KG-RAG outperforms the original RAG model across multiple evaluation metrics. On the Natural Questions dataset, the ROUGE-L score of the KG-RAG model improves from 41.2 to 46.9, the BLEU score rises from 31.5 to 38.7, and the FactScore increases by 13.6%, significantly enhancing the knowledge consistency of the generated text. In the PubMedQA task, KG-RAG achieves an accuracy rate of 81% in medical question answering. 3%, an improvement of 6.8% points over RAG, demonstrates its advantage in knowledge reasoning within specialized fields. Furthermore, case studies show that KG-RAG can effectively integrate entity paths from knowledge graphs to generate more logical and factual answers in complex question-answering tasks. This method has broad application prospects in intelligent question-answering systems, multi-turn conversations, and educational Q&A scenarios. Future research will consider introducing dynamic knowledge update mechanisms and multimodal graph information to further enhance the capabilities and adaptability of KG-RAG in real-world tasks.
Journal Article
Chatting with ChatGPT : the collection 1
ChatGPT is an artificial intelligence (AI) chatbot, a software application that aims to mimic human conversation through text or voice interactions, launched as a prototype on November 30, 2022, garnering attention for its detailed responses and articulate answers across many domains of knowledge. ChatGPT can write and debug computer programs, mimic the style of celebrity CEOs and write business pitches, compose music, teleplays, fairy tales and student essays, answer test questions (sometimes, depending on the test, at a level above the average human test-taker), write poetry and song lyrics, translate and summarize text, emulate a Linux system; simulate entire chat rooms, play games like tic-tac-toe and simulate an ATM. This is a collection of questions and answers from ChatGPT.
Book
CoQUAD: a COVID-19 question answering dataset system, facilitating research, benchmarking, and practice
Background
Due to the growing amount of COVID-19 research literature, medical experts, clinical scientists, and researchers frequently struggle to stay up to date on the most recent findings. There is a pressing need to assist researchers and practitioners in mining and responding to COVID-19-related questions on time.
Methods
This paper introduces CoQUAD, a question-answering system that can extract answers related to COVID-19 questions in an efficient manner. There are two datasets provided in this work: a reference-standard dataset built using the CORD-19 and LitCOVID initiatives, and a gold-standard dataset prepared by the experts from a public health domain. The CoQUAD has a Retriever component trained on the BM25 algorithm that searches the reference-standard dataset for relevant documents based on a question related to COVID-19. CoQUAD also has a Reader component that consists of a Transformer-based model, namely MPNet, which is used to read the paragraphs and find the answers related to a question from the retrieved documents. In comparison to previous works, the proposed CoQUAD system can answer questions related to early, mid, and post-COVID-19 topics.
Results
Extensive experiments on CoQUAD Retriever and Reader modules show that CoQUAD can provide effective and relevant answers to any COVID-19-related questions posed in natural language, with a higher level of accuracy. When compared to state-of-the-art baselines, CoQUAD outperforms the previous models, achieving an exact match ratio score of 77.50% and an F1 score of 77.10%.
Conclusion
CoQUAD is a question-answering system that mines COVID-19 literature using natural language processing techniques to help the research community find the most recent findings and answer any related questions.
Journal Article
A comprehensive survey of techniques for developing an Arabic question answering system
The question-answering system (QAS) aims to produce a response to a query using information from a text corpus. Arabic is a complex language. However, it has more than 450 million native speakers across the globe. The Saudi Arabian government encourages organizations to automate their routine activities to provide adequate services to their stakeholders. The performance of current Arabic QASs is limited to the specific domain. An effective QAS retrieves relevant responses from structured and unstructured data based on the user query. Many QAS studies categorized QASs according to factors, including user queries, dataset characteristics, and the nature of the responses. A more comprehensive examination of QASs is required to improve the QAS development according to the present QAS requirements. The current literature presents the features and classifications of the Arabic QAS. There is a lack of studies to report the techniques of Arabic QAS development. Thus, this study suggests a systematic literature review of strategies for developing Arabic QAS. A total of 617 articles were collected, and 40 papers were included in the proposed review. The outcome reveals the importance of the dataset and the deep learning techniques used to improve the performance of the QAS. The existing systems depend on supervised learning methods that lower QAS performance. In addition, the recent development of machine learning techniques encourages researchers to develop unsupervised QAS.
Journal Article
Intelligent Question-Answering System for New Energy Vehicles Integrating Deep Semantic Parsing and Knowledge Graphs
The new energy vehicle (NEV) industry generates massive multi-source heterogeneous data. To overcome traditional database limitations in terminology disambiguation and multi-hop reasoning, this paper proposes a knowledge graph (KG)-based question-answering (QA) architecture. Three primary domain challenges are addressed: First, to tackle the poor semantic extraction of informal diagnostic texts, a deep semantic parsing network (BERT-BiLSTM-CRF) is integrated to extract high-precision knowledge from 150,000 real-world maintenance records. Second, to solve topological redundancy, the Labeled Property Graph (LPG) specification is employed to encapsulate parameters of 2157 vehicle models as internal attributes, significantly streamlining complex multi-hop reasoning. Finally, to enhance limited reasoning capabilities, an intent classification module (TextCNN) automatically translates natural language into graph queries, enabling deep fault tracing across up to five semantic levels. Experimental results demonstrate 98% and 93% accuracy in entity-relation recognition and intent classification, respectively. The resulting KG (8274 nodes, 14,488 edges) establishes a scalable paradigm for intelligent diagnostic reasoning in complex vertical domains.
Journal Article
RS-LLaVA: A Large Vision-Language Model for Joint Captioning and Question Answering in Remote Sensing Imagery
In this paper, we delve into the innovative application of large language models (LLMs) and their extension, large vision-language models (LVLMs), in the field of remote sensing (RS) image analysis. We particularly emphasize their multi-tasking potential with a focus on image captioning and visual question answering (VQA). In particular, we introduce an improved version of the Large Language and Vision Assistant Model (LLaVA), specifically adapted for RS imagery through a low-rank adaptation approach. To evaluate the model performance, we create the RS-instructions dataset, a comprehensive benchmark dataset that integrates four diverse single-task datasets related to captioning and VQA. The experimental results confirm the model’s effectiveness, marking a step forward toward the development of efficient multi-task models for RS image analysis.
Journal Article
Educational QA System-Oriented Answer Selection Model Based on Focus Fusion of Multi-Perspective Word Matching
Question-answering systems have become an important tool for learning and knowledge acquisition. However, current answer selection models often rely on representing features using whole sentences, which leads to neglecting individual words and losing important information. To address this challenge, the paper proposes a novel answer selection model based on focus fusion of multi-perspective word matching. First, according to the different combination relationships between sentences, focus distribution in terms of words is obtained from the matching perspectives of serial, parallel, and transfer. Then, the sentence’s key position information is inferred from its focus distribution. Finally, a method of aligning key information points is designed to fuse the focus distribution for each perspective, which obtains match scores for each candidate answer to the question. Experimental results show that the proposed model significantly outperforms the Transformer encoder fine-tuned model based on contextual embedding, achieving a 4.07% and 5.51% increase in MAP and a 1.63% and 4.86% increase in MRR, respectively.
Journal Article