Interactive Question Answering Research Articles

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.

Interactive Question Answering Systems: Literature Review

Question-answering systems are recognized as popular and frequently effective means of information seeking on the web. In such systems, information seekers can receive a concise response to their queries by presenting their questions in natural language. Interactive question answering is a recently proposed and increasingly popular solution that resides at the intersection of question answering and dialogue systems . On the one hand, the user can ask questions in normal language and locate the actual response to her inquiry; on the other hand, the system can prolong the question-answering session into a dialogue if there are multiple probable replies, very few, or ambiguities in the initial request. By permitting the user to ask more questions, interactive question answering enables users to interact with the system and receive more precise results dynamically. This survey offers a detailed overview of the interactive question-answering methods that are prevalent in current literature. It begins by explaining the foundational principles of question-answering systems, hence defining new notations and taxonomies to combine all identified works inside a unified framework. The reviewed published work on interactive question-answering systems is then presented and examined in terms of its proposed methodology, evaluation approaches, and dataset/application domain. We also describe trends surrounding specific tasks and issues raised by the community, so shedding light on the future interests of scholars. Our work is further supported by a GitHub page synthesizing all the major topics covered in this literature study. https://sisinflab.github.io/interactive-question-answering-systems-survey/

FFA-GPT: an automated pipeline for fundus fluorescein angiography interpretation and question-answer

Fundus fluorescein angiography (FFA) is a crucial diagnostic tool for chorioretinal diseases, but its interpretation requires significant expertise and time. Prior studies have used Artificial Intelligence (AI)-based systems to assist FFA interpretation, but these systems lack user interaction and comprehensive evaluation by ophthalmologists. Here, we used large language models (LLMs) to develop an automated interpretation pipeline for both report generation and medical question-answering (QA) for FFA images. The pipeline comprises two parts: an image-text alignment module (Bootstrapping Language-Image Pre-training) for report generation and an LLM (Llama 2) for interactive QA. The model was developed using 654,343 FFA images with 9392 reports. It was evaluated both automatically, using language-based and classification-based metrics, and manually by three experienced ophthalmologists. The automatic evaluation of the generated reports demonstrated that the system can generate coherent and comprehensible free-text reports, achieving a BERTScore of 0.70 and F1 scores ranging from 0.64 to 0.82 for detecting top-5 retinal conditions. The manual evaluation revealed acceptable accuracy (68.3%, Kappa 0.746) and completeness (62.3%, Kappa 0.739) of the generated reports. The generated free-form answers were evaluated manually, with the majority meeting the ophthalmologists’ criteria (error-free: 70.7%, complete: 84.0%, harmless: 93.7%, satisfied: 65.3%, Kappa: 0.762–0.834). This study introduces an innovative framework that combines multi-modal transformers and LLMs, enhancing ophthalmic image interpretation, and facilitating interactive communications during medical consultation.

ICGA-GPT: report generation and question answering for indocyanine green angiography images

BackgroundIndocyanine green angiography (ICGA) is vital for diagnosing chorioretinal diseases, but its interpretation and patient communication require extensive expertise and time-consuming efforts. We aim to develop a bilingual ICGA report...

Research on the model of automatic recognition and natural language question-answer system for traditional Chinese medicine tongue images based on LLMs

Large Language Models (LLMs) have recently demonstrated their potential in clinical applications by providing valuable medical knowledge and recommendations. Traditional Chinese tongue diagnosis, one of the "Four Diagnoses," is an essential method for traditional Chinese medicine diagnosis. This paper builds upon tongue image classification technology and utilizes natural language processing and image recognition techniques to enhance the discrimination and analysis of traditional Chinese tongue images through learning and inference. We propose a method to integrate LLMs into the tongue image automatic recognition model and use them in interactive question-answering by summarizing and reorganizing information in natural language text format.

PaniniQA: Enhancing Patient Education Through Interactive Question Answering

Abstract A patient portal allows discharged patients to access their personalized discharge instructions in electronic health records (EHRs). However, many patients have difficulty understanding or memorizing their discharge instructions (Zhao et al., 2017). In this paper, we present PaniniQA, a patient-centric interactive question answering system designed to help patients understand their discharge instructions. PaniniQA first identifies important clinical content from patients’ discharge instructions and then formulates patient-specific educational questions. In addition, PaniniQA is also equipped with answer verification functionality to provide timely feedback to correct patients’ misunderstandings. Our comprehensive automatic & human evaluation results demonstrate our PaniniQA is capable of improving patients’ mastery of their medical instructions through effective interactions.1

Survey on the Research Progress and Development Trend of Vision-and-Language Navigation

Vision-and-language navigation is a newly emerging research topic developing rapidly in recent years, and it is one of the representative research tasks in the frontier field of vision-language interaction. The goal of this task is to realize autonomous navigation based on visual perception of environment according to language instructions given by human. This paper reviews the recent progress in vision-and-language navigation. Firstly, the research content of this task is introduced, and the three main problems and challenges of cross-modal semantic alignments, semantic understanding and reasoning, and generalization ability enhancement are analyzed. Secondly, commonly-used datasets and evaluation metrics are listed. Thirdly, the research progress of this task is summarized from four aspects of imitation learning, reinforcement learning, self-supervised learning and other methods, and the effects of the typical solutions are carefully compared and analyzed. Fourthly, the current research trends of this task are discussed, which mainly include continuous environment navigation, advanced complex instruction comprehension and common sense reasoning. Finally, the future development directions such as 3D visual-and-language navigation, embodied question answering and interactive question answering are further discussed and prospected.

Research on an Interactive Question Answering System of Artificial Intelligence Customer Service Based on Word2Vec

In order to reduce the labor cost pressure of telecom operators' customer service and improve the service quality, the natural language analysis technology based on artificial intelligence technology will realize the automatic question and answer customer service.This paper proposes to obtain word vectors based on Word2vec model. By comparing the word vectors under different training model parameters, the results show that the low-frequency word threshold plays a better role in controlling the number of the final trained word vectors. The training results of SKIP-GRAM model are better than that of CBOW and the word list is more regular. Under the condition of making full use of the existing customer service knowledge resources, the new system will realize the goal of innovating service means, expanding customer service channels, diverting customer service pressure and improving service efficiency.

Question Answering Over Knowledge Graphs: A Case Study in Tourism

Over the recent years, a large number of knowledge graphs (KGs) have been developed to store and present small and medium enterprises’ data in the form of subject-predicate-object triples. The KGs are not easily accessible to end-users because they need an understanding of query languages and KGs’ structures. To assist end-users in accessing these KGs, question answering over KGs targets to provide answers for natural language questions (NLQs). This paper proposes an approach to answer questions over small and medium scaled KGs based on graph isomorphism in two phases: (1) offline phase and (2) semantic parsing phase. In the offline phase, a semi-automated solution is proposed to generate NLQs and their answers, which are used to train machine learning models employed in the next phase. In the semantic parsing phase, a given input NLQ is mapped into a query pattern according to its grammatical structure. Each query pattern contains some slots that need to be filled with corresponding entities, classes and relations from the KG. While string and semantic similarity metrics are applied to identify the entities and classes, the probability distribution of the relations is used to extract the relations. The Cartesian product of the identified entities, classes and relations is utilized to fill the slots, derive SPARQL queries and finally retrieve the answers. To evaluate the proposed approach, we use SalzburgerLand KG, a real KG describing touristic entities of the region of Salzburg, Austria. Our results show that the approach improves the end-to-end user experience in terms of interactive question answering and performance.

Automated Question-Answering for Interactive Decision Support in Operations & Maintenance of Wind Turbines

Intelligent question-answering (QA) systems have witnessed increased interest in recent years, particularly in their ability to facilitate information access, data interpretation or decision support. The wind energy sector is one of the most promising sources of renewable energy, yet turbines regularly suffer from failures and operational inconsistencies, leading to downtimes and significant maintenance costs. Addressing these issues requires rapid interpretation of complex and dynamic data patterns under time-critical conditions. In this article, we present a novel approach that leverages interactive, natural language-based decision support for operations & maintenance (O&M) of wind turbines. The proposed interactive QA system allows engineers to pose domain-specific questions in natural language, and provides answers (in natural language) based on the automated retrieval of information on turbine sub-components, their properties and interactions, from a bespoke domain-specific knowledge graph. As data for specific faults is often sparse, we propose the use of paraphrase generation as a way to augment the existing dataset. Our QA system leverages encoder-decoder models to generate Cypher queries to obtain domain-specific facts from the KG database in response to user-posed natural language questions. Experiments with an attention-based sequence-to-sequence (Seq2Seq) model and a transformer show that the transformer accurately predicts up to 89.75% of responses to input questions, outperforming the Seq2Seq model marginally by 0.76%, though being 9.46 times more computationally efficient. The proposed QA system can help support engineers and technicians during O&M to reduce turbine downtime and operational costs, thus improving the reliability of wind energy as a source of renewable energy.

Preprocessing of normative documents for interactive question answering

Every larger organisation must establish a set of normative documents to control its processes and describe solutions to common problems. These documents are usually formally written and hard to read. This leads to the necessity off different customer services. Nowadays, a lot of companies are developing chatbots to automate first-line customer support. If a company does not have a large question–answer dataset to build a chatbot, the answers can be automatically answered directly from the documents. However, we found that the automatic answering usually does not work well on the normative documents. In this paper, we describe a novel method for preprocessing of normative documents in order to use them for such automatic question answering. Our method efficiently exploits the strict document structure that is typical for normative documents. The method enabled us to increase the recall from 35% to 84% (for paragraph-size answers) on selected normative documents from university and bank domains.

Virtual assistant upper respiratory tract infection education based natural language

The high incidence of upper respiratory tract infection (URTI) in Indonesia requires an efficient healthcare solution to maintain human wellbeing. The e-health education model proposed in this paper is a virtual assistant in the form of an interactive question and answer system assistant virtual interactive question answering (AVIQA) with a natural language approach. AVIQA is a form of problem-solving approach to design some aspects of education and consultation in helping parents to recognize symptoms and dealing with several preventive ac tions for toddlers when exposed to Upper Respiratory Tract Infection. The technologies proposed for the development of AVIQA include (i) Representation of sentence meanings to build an URTI knowledge base; (ii) Design of dialogue models for interactive consultation using a combination between information state and frame base model and (iii) development of IQA based on casebase reasoning and semantic role labelling. The purpose of developing this technology is to achieve a system that is capable of assisting the users especially mothers in searching for information, reducing user time compared to reading a document, and providing a good advice for finding the right answers, which then can be constructed from a management model prototype information for the education and independent consultation for users. The final result of this study is e-health education system based Indonesian natural language that has an ability in terms of health consultations especially health of children under five in Acute Respiratory Infection disease. This system is expected to have a significant impact on the ability of a mother to recognize symptoms and deal with children attacked by URTI.

Determining Reliability in Interactive Question Answering Systems by Regression

Determining Reliability in Interactive Question Answering Systems by Regression

Virtual assistant upper respiratory tract infection education based natural language

The high incidence of Upper Respiratory Tract Infection (URTI) in Indonesia requires an efficient healthcare solution to maintain human wellbeing. The e-health education model proposed in this paper is a virtual assistant in the form of an interactive question and answer system (Assistant Virtual Interactive Question Answering = AVIQA) with a natural language approach. AVIQA is a form of problem-solving approach to design some aspects of education and consultation in helping parents to recognize symptoms and dealing with several preventive actions for toddlers when exposed to Upper Respiratory Tract Infection. The technologies proposed for the development of AVIQA include (i) Representation of sentence meanings to build an URTI knowledge base; (ii) Design of dialogue models for interactive consultation using a combination between information state and frame base model and (iii) development of IQA based on casebase reasoning and semantic role labelling. The purpose of developing this technology is to achieve a system that is capable of assisting the users especially mothers in searching for information, reducing user time compared to reading a document, and providing a good advice for finding the right answers, which then can be constructed from a management model prototype information for the education and independent consultation for users. The final result of this study is e-health education system based Indonesian natural language that has an ability in terms of health consultations especially health of children under five in Acute Respiratory Infection disease. This system is expected to have a significant impact on the ability of a mother to recognize symptoms and deal with children attacked by URTI

Generating Explorable Narrative Spaces with Answer Set Programming

Previous approaches to narrative generation have required a new planner implementation for each set of constraints deemed relevant to the narrative domain, each consisting of thousands of lines of code and supporting one primary mode of interaction: fully specifying a domain and problem, and receiving a plan as output. We present a lightweight, flexible narrative planner written with Answer Set Programming, designed specifically to support constraint-based narrative generation, show how it generalizes previous approaches, and show how it can be easily extended with notions of thematic plot schema such as “betrayal.” Finally, we demonstrate how the ASP model can be explored through interactive question answering, where answers take the form of generated narratives. In the long term, we intend this work to support understanding of complex rule systems through interactive exploration.

Ontology based Baysian network for clinical specialty supporting in interactive question answering systems

PurposeThis study aims to provide an ontology based Baysian network for clinical specialty supporting. As a knowledge base, ontology plays an essential role in domain applications especially in expert systems. Interactive question answering systems are suitable for personal domain consulting and recommended for real-time usage. Clinical specialty supporting for dispatching patients can assist hospitals to locate desired treatment departments for individuals relevant to their syndromes and disease efficiently and effectively. By referring to interactive question answering systems, individuals can understand how to alleviate time and medical resource wasting according to recommendations from medical ontology-based systems.Design/methodology/approachThis work presents an ontology based on clinical specialty supporting using an interactive question answering system to achieve this aim. The ontology incorporates close temporal associations between words in input query to represent word co-occurrence relationships in concept space. The patterns defined in lexicon chain mechanism are further extracted from the query words to infer related concepts for treatment departments to retrieve information.FindingsThe precision and recall rates are considered as the criteria for model optimization. Finally, the inference-based interactive question answering system using natural language interface is adopted for clinical specialty supporting, and indicates its superiority in information retrieval over traditional approaches.Originality/valueFrom the observed experimental results, we find the proposed method is useful in practice especially in treatment department decision supporting using metrics precision and recall rates. The interactive interface using natural language dialogue attracts the users’ attention and obtains a good score in mean opinion score measure.

Answering contextual questions based on ontologies and question templates

Contextual question answering (CQA), in which user information needs are satisfied through an interactive question answering (QA) dialog, has recently attracted more research attention. One challen...

Using cross-evaluation to evaluate interactive QA systems

In this article, we report on an experiment to assess the possibility of rigorous evaluation of interactive question-answering (QA) systems using the cross-evaluation method. This method takes into account the effects of tasks and context, and of the users of the systems. Statistical techniques are used to remove these effects, isolating the effect of the system itself. The results show that this approach yields meaningful measurements of the impact of systems on user task performance, using a surprisingly small number of subjects and without relying on predetermined judgments of the quality, or of the relevance of materials. We conclude that the method is indeed effective for comparing end-to-end QA systems, and for comparing interactive systems with high efficiency.

Course ontology-based user’s knowledge requirement acquisition from behaviors within e-learning systems

User’s knowledge requirement acquisition and analysis are very important for a personalized or user-adaptive learning system. Two approaches to capture user’s knowledge requirement about course content within an e-learning system are proposed and implemented in this paper. The first approach is based on the historical data accumulated by an interactive question-answering process. The association space is proposed to record and formalize the historical interactive information which is used to compute user’s knowledge requirement. The second approach is based on user’s reading behavior logs in the process of reading e-documents. User’s reading actions including underline, highlight, circle, annotation and bookmark, are used to compute user’s knowledge requirement. Two experiments are conducted to implement the two proposed approaches and acquire the user’s knowledge requirement. The evaluation results show that the user models computed by two approaches are consistent and can reflect user’s real knowledge requirements accurately.

Designing an interactive open-domain question answering system

AbstractInteractive question answering (QA), where a dialogue interface enables follow-up and clarification questions, is a recent although long-advocated field of research. We report on the design and implementation of YourQA, our open-domain, interactive QA system. YourQA relies on a Web search engine to obtain answers to both fact-based and complex questions, such as descriptions and definitions. We describe the dialogue moves and management model making YourQA interactive, and discuss the architecture, implementation and evaluation of its chat-based dialogue interface. Our Wizard-of-Oz study and final evaluation results show how the designed architecture can effectively achieve open-domain, interactive QA.