The usage and amount of information available on the internet increase over the past decade. This digitization leads to the need for automated answering system to extract fruitful information from redundant and transitional knowledge sources. Such systems are designed to cater the most prominent answer from this giant knowledge source to the user’s query using natural language understanding (NLU) and thus eminently depends on the Question-answering(QA) field. Question answering involves but not limited to the steps like mapping of user’s question to pertinent query, retrieval of relevant information, finding the best suitable answer from the retrieved information etc. The current improvement of deep learning models evince compelling performance improvement in all these tasks. In this review work, the research directions of QA field are analyzed based on the type of question, answer type, source of evidence-answer, and modeling approach. This detailing followed by open challenges of the field like automatic question generation, similarity detection and, low resource availability for a language. In the end, a survey of available datasets and evaluation measures is presented.

Open domain question answering (OpenQA) tasks have been recently attracting more and more attention from the natural language processing (NLP) community. In this work, we present the first free-form multiple-choice OpenQA dataset for solving medical problems, MedQA, collected from the professional medical board exams. It covers three languages: English, simplified Chinese, and traditional Chinese, and contains 12,723, 34,251, and 14,123 questions for the three languages, respectively. We implement both rule-based and popular neural methods by sequentially combining a document retriever and a machine comprehension model. Through experiments, we find that even the current best method can only achieve 36.7%, 42.0%, and 70.1% of test accuracy on the English, traditional Chinese, and simplified Chinese questions, respectively. We expect MedQA to present great challenges to existing OpenQA systems and hope that it can serve as a platform to promote much stronger OpenQA models from the NLP community in the future.

Existing Knowledge Graph (KG) models for commonsense question answering present two challenges: (i) existing methods retrieved entities related to questions from the knowledge graph, which may extract noise and irrelevant nodes, and (ii) lack of interaction representation between questions and graph entities. However, current methods mainly focus on retrieving relevant entities with some noisy and irrelevant nodes. In this paper, we propose a novel Retrieval-augmented Knowledge Graph (RAKG) model, which solves the above issues through two key innovations. First, we leverage the density matrix to make the model reason along the corrected knowledge path and extract an enhanced knowledge graph subgraph. Second, we fuse representations of questions and graph entities through a bidirectional attention strategy, in which two representations fuse and update by Graph Convolutional Network (GCN). To evaluate the performance of our method, we conduct experiments on two widely-used benchmark datasets CommonsenseQA and OpenBookQA. The case study gives insight into findings that the augmented subgraph provides reasoning along the corrected knowledge path for question answering.

Language bias stands as a noteworthy concern in Visual Question Answering (VQA), wherein models tend to rely on spurious correlations between questions and answers for prediction. This prevents the models from effectively generalizing, leading to a decrease in performance. To address this bias, we propose a novel modality fusion collaborative de-biasing algorithm (CoD). In our approach, bias is considered as the model’s neglect of information from a particular modality during prediction. We employ a collaborative training approach to facilitate mutual modeling between different modalities, achieving efficient feature fusion and enabling the model to fully leverage multi-modal knowledge for prediction. Our experiments on various datasets, including VQA-CP v2, VQA v2, and VQA-VS, using different validation strategies, demonstrate the effectiveness of our approach. Notably, employing a basic baseline model resulted in an accuracy of 60.14% on VQA-CP v2.

This study innovates upon the field of dialog-driven query resolution (DDQR) utilizing knowledge graphs (KGs). Traditional methods in DDQR predominantly depend on fully supervised signals that presuppose the existence of perfect logical forms for queries. This reliance on gold logical forms for answer extraction is impractical in diverse real-world applications. When such forms are absent, contemporary methods, which lean on weak supervisory signals or employ heuristic and reinforcement strategies, recast DDQR as a knowledge graph path optimization problem. Despite the non-availability of gold logical forms, the rich conversational context provided by comprehensive dialog histories and domain-specific knowledge can be leveraged to optimize path selection in KGs effectively. We introduce an advanced method, termed CONVEX (CONVersational EXploration), which utilizes contrastive learning for path ranking. CONVEX addresses critical challenges by enabling learning under weak supervision and integrating the conversational context to enhance the representation quality for more effective path discrimination. Extensive evaluations of CONVEX on established benchmarks demonstrate its superiority across various metrics over current methods, notably improving Mean Reciprocal Rank (MRR) and Hit@5 by up to 20 and 36 percentage points respectively.

In this study, we aim to explore whether rephrasing enhances the performance of advanced question answering systems in terms of accuracy. Initially, we analyze the effectiveness of Bidirectional Encoder Representations from Transformers (BERT)—a widely used pre-trained language model—when presented with rephrased questions and documents containing distracting details. Our findings reveal that BERT exhibits excessive sensitivity to such instances, prompting us to investigate potential strategies for mitigating this sensitivity. To address the observed decline in performance, we propose a refinement approach for BERT, incorporating techniques such as data augmentation and multitask learning. Specifically, given a question and its context, we generate a series of paraphrases through back-translation. Alongside minimizing the loss between the predicted answer distributions for the original questions—we also minimize the supervised loss associated with the augmented questions. Furthermore, we introduce an auxiliary objective aimed at minimizing the unsupervised loss between the answer distributions of the original and augmented questions. Notably, this auxiliary loss is unsupervised, as it does not directly rely on labels corresponding to the augmented examples. To compute this unsupervised loss, we employ measures such as symmetric Kullback-Leibler divergence and the Jensen-Shannon distance, serving as regularization techniques for the model. The findings revealed that the supervised model exhibited superior performance compared to both the original and our proposed model. However, our proposed model demonstrated a nearly 2% enhancement in both Exact Match (EM) and F1 scores when tested on a paraphrased development set that we formulated. This suggests the potential effectiveness of our proposed approach in enhancing model accuracy and performance.

The commonly-used large-scale knowledge bases have been facing challenges in open domain question answering tasks which are caused by the loose knowledge association and weak structural logic of triplet-based knowledge. To find a way out of this dilemma, this work proposes a novel metaknowledge enhanced approach for open domain question answering. We design an automatic approach to extract metaknowledge and build metaknowledge network from Wiki documents. For the purpose of representing the directional weighted graph with hierarchical and semantic features, we present an original graph encoder GE4MK to model the metaknowledge network. Then a metaknowledge enhanced graph reasoning model MEGr-Net is proposed for question answering, which aggregates both relational and neighboring interactions comparing with R-GCN and GAT. Experiments have proved the improvement of metaknowledge over main-stream triplet-based knowledge. We have found that the graph reasoning models and pre-trained language models also have influences on the metaknowledge enhanced question answering approaches.

Visual question answering (VQA) is receiving increasing attention from researchers in both the computer vision and natural language processing fields. There are two key components in the VQA task: feature extraction and multi-modal fusion. For feature extraction, we introduce a novel co-attention scheme by combining Sentence-guide Word Attention (SWA) and Question-guide Image Attention (QIA) in a unified framework. To be specific, the textual attention SWA relies on the semantics of the whole question sentence to calculate contributions of different question words for text representation. For the multi-modal fusion, we propose a “Cross-modal Multistep Fusion (CMF)” network to generate multistep features and achieve multiple interactions for two modalities, rather than focusing on modeling complex interactions between two modals like most current feature fusion methods. To avoid the linear increase of the computational cost, we share the parameters for each step in the CMF. Extensive experiments demonstrate that the proposed method can achieve competitive or better performance than the state-of-the-art.

Understanding complex Portable Document Format (PDF) files, such as research papers, clinical reports, and scientific manuals, is often a time-consuming endeavor. While significant progress has been made in developing question-answering (QA) systems that yield contextually relevant responses, the creation of a comprehensive end-to-end machine learning model capable of addressing intricate questions remains a formidable challenge. These systems typically rely on substantial labeled training data to effectively train their foundational models for specific tasks. However, assembling such datasets is particularly challenging for complex documents, including annual reports from major technology companies. In this paper, we address this issue by developing a QA system specifically designed for PDF documents, focusing on the domains of finance, biomedicine, and scientific literature. We manually curated datasets from these areas for evaluation purposes and utilized pre-trained Bidirectional Encoder Representations from Transformers (BERT) models from the Hugging Face library. The models were evaluated using the F1 score, achieving a notable score of 44% with the BERT Large model.

With the continuous breakthrough of natural language processing, the application of intelligent question answering technology in electric power system has attracted wide attention. However, at present, the traditional question answering system has poor performance and is difficult to be applied in engineering practice. This paper proposes an improved BERTserini algorithm for intelligent answering of electric power regulations based on a BERT model. The proposed algorithm is implemented in two stages. The first stage is the text segmentation stage, where a multi-document long text preprocessing technique is utilized that accommodates the rules and regulations text, and then Anserini is used to extract paragraphs with high relevance to the given question. The second stage is answer generation and source retrieval stage, where a two-step fine-tuning based on the Chinese BERT model is applied to generate precise answers based on given questions, while the information regarding documents, chapters, and page numbers of these answers are also output simultaneously. The algorithm proposed in this paper eliminates the necessity for manual organization of professional question-answer pairs, thereby effectively reducing the manual labor cost compared to traditional question answering systems. Additionally, this algorithm exhibits a higher degree of exact match rate and a faster response time for providing answers.

Chatbots have gained widespread popularity for their task automation capabilities and consistent availability in various domains, including education. However, their ability to adapt to the continuously evolving and dynamic nature of knowledge is limited. This research investigates the implementation of an internet wizard to enhance the knowledge base of an open-domain question-answering chatbot. The proposed approach leverages search engines, particularly Google, and its features, including feature snippets, knowledge graph, and organic search, in conjunction with data science and natural language models. This mechanism empowers the chatbot to dynamically access the extensive and up-to-date knowledge available on the web, enabling the provision of real-time and pertinent answers to user queries sourced from web documents. A pilot study in a higher education context evaluated the chatbot's mechanism and features, confirming its proficiency in generating responses across a broad range of educational and non-educational topics. Positive feedback and high user satisfaction validate these findings. Notably, the chatbot's dynamic feature of retrieving related or follow-up questions from search engines significantly enhances student engagement and facilitates exploration of supplementary information beyond the curriculum.

In the dynamic landscape of E-commerce, the proliferation of user-generated queries regarding products highlights the critical need for advanced automatic question answering (AQA) systems. These systems are instrumental in harnessing the vast array of information available online to deliver immediate and informative responses to potential buyers. Recognizing the complexity of such queries, which often require synthesis of reviews, product specifications, and responses to similar questions, we introduce a sophisticated model, the Comprehensive E-commerce Answer Generation System (CEAGS). This model adeptly navigates the challenges posed by irrelevant data and sentiment ambiguity in user-generated content. Our approach leverages a dual-phase process of relevance determination and sentiment clarity, setting the stage for a transformative response generation mechanism. Empirical analyses reveal the superiority of CEAGS, with our relevance assessment framework outstripping existing models by a notable margin in precision metrics, and our answer generation module achieving unprecedented gains in content preservation and coherence. Notably, CEAGS marks a pioneering contribution to the E-commerce domain by integrating disparate information sources to formulate responses that are not only accurate but also contextually rich and user-centric.

Limiting training data in low-resource languages is a barrier to Natural Language Processing (NLP). Regardless, languages with thousands of users worldwide require improved NLP capabilities. The Table-to-Text task—typically develops natural language descriptions using data tables, tests model reasoning abilities—although it is especially tough in multi-language settings. System output frequently lack credit to their underlying data. Intermediate planning strategies—which include Question-Answer (QA) blueprints—improving summarization tasks by presenting related QA pair prior to verbalization. Therefore, this study analyses whether QA blueprints improve multilingual Table-to-Text output attribution. An enlarged multilingual dataset, encompassing African languages, contains QA blueprints that were produced and filtered heuristically. This dataset is used to fine-tune sequence-to-sequence model (transformers)—both with and without blueprints. Two configurations are evaluated—English reference blueprints with language target verbalization and modified blueprints. These results show that English-only models benefit from blueprints, whereas multi language models cannot. Errors in machine-translating blueprints provide challenges, as do models that rely on their generated blueprints.

There are some controversies about 2G bioethanol and it is in need of a reliable test data in order to make a further analysis and proof. In collecting basic data from three classes of typical raw materials, such as wheat, maize stalk juice, and straw, it was found that 4.32 tons straw or 3.358 tons wheat is needed to produce 1-ton bioethanol. Using the coefficient of variation calculation and analysis method, it is able to obtain the C.V. value of straw fermentation efficiency 0.08932<0.15, indicating the fermentation technology and process of 2G bioethanol is already quite mature and reliable, without risk, and also with a raw material cost advantage. There is a problem in that the C.V. value of straw volume is 1.2648>0.95, indicating 2G bioethanol is in an extremely high-risk area. Using the straw volume calculation method, building and its costs – capital expenditure of 2G bioethanol plant is approximately seven times that of a wheat ethanol plant. This should be some of the important reasons why it is noncompetitive, extremely high price, and requiring government subsidies. Straw volume data study has caused the 2G bioethanol plant to require more cement, steel, equipment, and other materials. Thus, there are ample reasons to question the CO2 emissions and its carbon footprint of 2G bioethanol plant. Actually, the volume is not the only existing problem, it is necessary to re-evaluate and discuss the definition of 2G bioethanol and its future.

Generating coherent and comprehensive responses remains a significant challenge Question-Answering (QA) systems when working with short answers especially for low-resourced languages like Farsi. We present a novel approach to expand these answers into complete, fluent responses, addressing the critical issue of limited Farsi resources and models. Our methodology employs a two-stage process: first, we develop a dataset using rule-based techniques on Farsi text, followed by a BERT-based ranking system to ensure fluency and comprehensibility. The resulting model demonstrates strong compatibility with existing QA systems, particularly those based on knowledge graphs. Notably, our system exhibits enhanced performance when integrated with large language models using Chain-of-Thought (CoT) prompting, leveraging detailed explanations rather than single-word answers. Our approach significantly improves response quality and coherence compared to baseline systems. We release our dataset to support further research in Farsi QA\footnote[1]{\href{https://huggingface.co/datasets/SLPL/syntran-fa}{https://huggingface.co/datasets/SLPL/syntran-fa}}.

In a global context, the story of the Jesuit compound in Shanghai, since its establishment by French Jesuits in 1847, reflected not only conflicts between rival powers in Europe but also the fight for their interests in the Eastern world. The Pope, who was stuck without legal status in the Vatican after 1861, was also seeking the chance to save the authority of the Church in the face of questions regarding the extent of his temporal power and the status of Rome in the context of Italian unification. As in the Reformation, a break-through in the east seemed to offer a solution for losses in Europe. However, the Jesuits to the East in the late 19th century were not only troops working and fighting on behalf of the Pope; their identities under the French Protectorate added complexity to an already complicated story involving not just the Church, but the course of world history.The female Catholic orders at the east bank of Zi-ka-wei compound became a unique window to approach the complexity.

Visual Question Generation (VQG) from images is a rising research topic in both fields of natural language processing and computer vision. Although there are some recent efforts towards generating questions from images in the open domain, the VQG task in the medical domain has not been well-studied so far due to the lack of labeled data. In this paper, we introduce a goal-driven VQG approach for radiology images called VQGRaD that generates questions targeting specific image aspects such as modality and abnormality. In particular, we study generating natural language questions based on the visual content of the image and on additional information such as the image caption and the question category. VQGRaD encodes the dense vectors of different inputs into two latent spaces, which allows generating, for a specific question category, relevant questions about the images, with or without their captions. We also explore the impact of domain knowledge incorporation (e.g., medical entities and semantic types) and data augmentation techniques on visual question generation in the medical domain. Experiments performed on the VQA-RAD dataset of clinical visual questions showed that VQGRaD achieves 61.86% BLEU score and outperforms strong baselines. We also performed a blinded human evaluation of the grammaticality, fluency, and relevance of the generated questions. The human evaluation demonstrated the better quality of VQGRaD outputs and showed that incorporating medical entities improves the quality of the generated questions. Using the test data and evaluation process of the ImageCLEF 2020 VQA-Med challenge, we found that relying on the proposed data augmentation technique to generate new training samples by applying different kinds of transformations, can mitigate the lack of data, avoid overfitting, and bring a substantial improvement in medical VQG.

We review the literature on medical discourse and attempt to build a computational model of it. Medical discourse sheds a light on communication structure of patient-doctor and other communication scenarios in healthcare and should be leveraged to facilitate and automate this communication when it is possible and practical. We propose a unified framework to represent communication discourse at the meta-level, where the subject of the communication is expressed in a language object. So far, the broad range of work on medical discourse is detached from computational discourse analysis, and we explore the possibilities of filling this gap and computationally treat the peculiarities of how information is passed between the agents in a hospital setting. We select the domain of question answering (QA) against a corpus of medical documents of diverse nature to evaluate our computational model of medical discourse. It turns out that applying specific structures obtained in medical discourse studies improves the relevance and efficiency of question answering.

Biomedical large language models (LLMs) have made significant strides, but their reliance on external retrieval mechanisms presents challenges in accuracy and computational efficiency. To address these issues, we propose MedRAG-Refine, a generative LLM designed specifically for the biomedical domain. Our model integrates a two-stage fine-tuning process, incorporating a self-reflection mechanism to improve reasoning quality. We evaluate our model on MedQA, MedMCQA, and MMLU datasets, demonstrating superior performance over state-of-the-art methods. Additionally, human evaluations confirm the enhanced accuracy and reasoning quality of our model in real-world medical tasks.

In the realm of artificial intelligence, knowledge graphs have become a fascinating area of research. Relationships between entities are depicted through a structural framework in knowledge graphs. In this paper, we propose to build a domain-specific medicine dictionary (DSMD) based on the principles of knowledge graphs. Our dictionary is composed of structured triples, where each entity is defined as a concept, and these concepts are interconnected through relationships. This comprehensive dictionary boasts more than 348,000 triples, encompassing over 20,000 medicine brands and 1,500 generic medicines. It offers a groundbreaking approach to storing and accessing medical data. Our dictionary facilitates various functionalities, including medicine brand information extraction, brand-specific queries, as well as queries involving two words or question answering. We anticipate that our dictionary will serve a broad spectrum of users, catering to both human users, such as diverse range of healthcare professionals as well as AI applications.

When an aircraft malfunctions, quickly and accurately identifying the faulty unit is essential for ensuring normal operation. Unfortunately, maintenance engineers often struggle to acquire the necessary fault-related knowledge due to poor management and utilization of aircraft fault documents. To address this issue, we introduce knowledge graph technology into the field of aircraft fault diagnosis, exploring its construction and application for effective knowledge management. Our work starts by analyzing the critical knowledge elements required for aircraft fault diagnosis and designing a schema layer for fault knowledge graphs. We then we then combine deep learning and heuristic rules to extract fault knowledge from both structured and unstructured data, enabling the construction of aircraft fault knowledge graphs. Finally, we develop a fault question-answering system based on fault knowledge graphs that can accurately give solutions to questions posed by maintenance engineers. Our practice demonstrates that knowledge graphs provide an effective means of managing aircraft fault knowledge, assisting engineers in locating fault reasons accurately and quickly.