Answer To Question Research Articles

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...

An Investigation into Presentation Apprehension among Non-English Major Students at a University in Hanoi

The study was carried out at Dai Nam University to measure the levels of presentation apprehension among non-English major students. The participants were 137 students of different disciplines. The study employs quantitative research design to obtain the answers for research questions. The first finding of the study shows that levels of presentation apprehension among non-English major students at Dai Nam University was M=3.06 which was at the medium level. In terms of variation of presentation apprehension by years of study, the findings reveal that there were significant differences. Year 1 (M = 3.82, SD = 0.25) was significantly larger than for Year 2 (M = 3.01, SD = 0.41), p < .001. For the main effect of year of study, the mean of presentation apprehension for Year 1 (M = 3.82, SD = 0.25) was significantly larger than for Year 3 (M = 2.29, SD = 0.39), p < .001. For the main effect of years of study, the mean of presentation apprehension for Year 2 (M = 3.01, SD = 0.41) was significantly larger than for Year 3 (M = 2.29, SD = 0.39), p < .001. The second finding of the study revealed that among the factors that lead to presentation apprehension, fear of being judged or criticized (Ft5), and lack of self-confidence (Ft6) were the main causes of anxiety M=3.05 and M=3.04 respectively. The finding also indicated that the factors of presentation apprehension varied by years of study.

Document Retrieval System for Biomedical Question Answering

In this paper, we describe our biomedical document retrieval system and answers extraction module, which is part of the biomedical question answering system. Approximately 26.5 million PubMed articles are indexed as a corpus with the Apache Lucene text search engine. Our proposed system consists of three parts. The first part is the question analysis module, which analyzes the question and enriches it with biomedical concepts related to its wording. The second part of the system is the document retrieval module. In this step, the proposed system is tested using different information retrieval models, like the Vector Space Model, Okapi BM25, and Query Likelihood. The third part is the document re-ranking module, which is responsible for re-arranging the documents retrieved in the previous step. For this study, we tested our proposed system with 6B training questions from the BioASQ challenge task. We obtained the best MAP score on the document retrieval phase when we used Query Likelihood with the Dirichlet Smoothing model. We used the sequential dependence model at the re-rank phase, but this model produced a worse MAP score than the previous phase. In similarity calculation, we included the Named Entity Recognition (NER), UMLS Concept Unique Identifiers (CUI), and UMLS Semantic Types of the words in the question to find the sentences containing the answer. Using this approach, we observed a performance enhancement of roughly 25% for the top 20 outcomes, surpassing another method employed in this study, which relies solely on textual similarity.

Meta-Interpretive LEarning with Reuse

Inductive Logic Programming (ILP) is a research field at the intersection between machine learning and logic programming, focusing on developing a formal framework for inductively learning relational descriptions in the form of logic programs from examples and background knowledge. As an emerging method of ILP, Meta-Interpretive Learning (MIL) leverages the specialization of a set of higher-order metarules to learn logic programs. In MIL, the input includes a set of examples, background knowledge, and a set of metarules, while the output is a logic program. MIL executes a depth-first traversal search, where its program search space expands polynomially with the number of predicates in the provided background knowledge and exponentially with the number of clauses in the program, sometimes even leading to search collapse. To address this challenge, this study introduces a strategy that employs the concept of reuse, specifically through the integration of auxiliary predicates, to reduce the number of clauses in programs and improve the learning efficiency. This approach focuses on the proactive identification and reuse of common program patterns. To operationalize this strategy, we introduce MILER, a novel method integrating a predicate generator, program learner, and program evaluator. MILER leverages frequent subgraph mining techniques to detect common patterns from a limited dataset of training samples, subsequently embedding these patterns as auxiliary predicates into the background knowledge. In our experiments involving two Visual Question Answering (VQA) tasks and one program synthesis task, we assessed MILER’s approach to utilizing reusable program patterns as auxiliary predicates. The results indicate that, by incorporating these patterns, MILER identifies reusable program patterns, reduces program clauses, and directly decreases the likelihood of timeouts compared to traditional MIL. This leads to improved learning success rates by optimizing computational efforts.

Knowledge-aware adaptive graph network for commonsense question answering

Knowledge-aware adaptive graph network for commonsense question answering

LeanContext: Cost-efficient domain-specific question answering using LLMs

Question-answering (QA) is a significant application of Large Language Models (LLMs), shaping chatbot capabilities across healthcare, education, and customer service. However, widespread LLM integration presents a challenge for small businesses due to the high expenses of LLM API usage. Costs rise rapidly when domain-specific data (context) is used alongside queries for accurate domain-specific LLM responses. Extracting context from domain-specific data is implemented by a Retrieval Augmented Generation (RAG) approach. One option is to summarize the RAG context by using LLMs and reduce the context. However, this can also filter out useful information that is necessary to answer some domain-specific queries. In this paper, we shift from human-oriented summarizers to AI model-friendly summaries. Our approach, LeanContext, efficiently extracts k key sentences from the context that are closely aligned with the query. The choice of k is neither static nor random; we introduce a reinforcement learning technique that dynamically determines k based on the query and context. The rest of the less important sentences are either reduced using a free open-source text reduction method or eliminated. We evaluate LeanContext against several recent query-aware and query-unaware context reduction approaches on prominent datasets (arxiv papers and BBC news articles, NarrativeQA). Despite cost reductions of 37.29% to 67.81%, LeanContext’s ROUGE-1 score decreases only by 1.41% to 2.65% compared to a baseline that retains the entire context (no summarization). LeanContext stands out for its ability to provide precise responses, outperforming competitors by leveraging open-source summarization techniques. Human evaluations of the responses further confirm and validate this superiority. Additionally, if open-source pre-trained LLM-based summarizers are used to reduce context (into human consumable summaries), LeanContext can further modify the reduced context to enhance the accuracy (ROUGE-1 score) by 13.22% to 24.61%.

INTEGRATING IMAGE FEATURES WITH CONVOLUTIONAL SEQUENCE-TO-SEQUENCE NETWORK FOR MULTILINGUAL VISUAL QUESTION ANSWERING

Visual question answering is a task that requires computers to give correct answers for the input questions based on the images. This task can be solved by humans with ease, but it is a challenge for computers. The VLSP2022-EVJVQA shared task carries the Visual question answering task in the multilingual domain on a newly released dataset UIT-EVJVQA, in which the questions and answers are written in three different languages: English, Vietnamese, and Japanese. We approached the challenge as a sequence-to-sequence learning task, in which we integrated hints from pre-trained state-of-the-art VQA models and image features with a convolutional sequence-to-sequence network to generate the desired answers. Our results obtained up to 0.3442 by F1 score on the public test set and 0.4210 on the private test set.

Cascade transformers with dynamic attention for video question answering

Visual question answering (VQA) has become a hot study topic with challenging motivation of correctly answering the videos or images questions in recent years. However, the existing VQA model mostly aimed at answering questions about images and performed poorly in the video question answering (VideoQA) domain. VideoQA needs to simultaneously consider the correlations between video frames and the dynamic information of multiple objects in video. Therefore, we propose a novel Cascade Transformers with Dynamic Attention for Video Question Answering (CTDA-QA), which aims to simultaneously solve the above considerations. Specifically, the proposed CTDA-QA model utilizes multiple transformers structure to encode videos for reasoning complex spatial and temporal information, which is different from the previous recurrent neural network methods. Besides, in order to effectively capture the dynamic information from various scenarios in videos, a flexible attention module has been proposed to explore the essential relations between objects in a dynamic timeline. Finally, to avoid spurious answers and fully explore the cross-modal relationships, a mixed-supervised learning strategy is designed for optimizing the reasoning tasks. The experiments on several benchmark video question–answer datasets clearly verify the performance and effectiveness of CTDA-QA, which contains the results in contrast to the state-of-the-art methods. Besides, the provided ablation study and visualization results further reveal the potential of CTDA-QA.

Natural Language Processing Tools for Romanian – Going Beyond a Low-Resource Language.

Advances in Natural Language Processing bring innovative instruments to the educational field to improve the quality of the didactic process by addressing challenges like language barriers and creating personalized learning experiences. Most research in the domain is dedicated to high-resource languages, such as English, while languages with limited coverage, like Romanian, are still underrepresented in the field. Operating on low-resource languages is essential to ensure equitable access to educational opportunities and to preserve linguistic diversity. Through continuous investments in developing Romanian educational instruments, we are rapidly going beyond a low-resource language. This paper presents recent educational instruments and frameworks dedicated to Romanian, leveraging state-of-the-art NLP techniques, such as building advanced Romanian language models and benchmarks encompassing tools for language learning, text comprehension, question answering, automatic essay scoring, and information retrieval. The methods and insights gained are transferable to other low-resource languages, emphasizing methodological adaptability, collaborative frameworks, and technology transfer to address similar challenges in diverse linguistic contexts. Two use cases are presented, focusing on assessing student performance in Moodle courses and extracting main ideas from students’ feedback. These practical applications in Romanian academic settings serve as examples for enhancing educational practices in other less-resourced languages.

MedChatZH: A tuning LLM for traditional Chinese medicine consultations

Generative Large Language Models (LLMs) have achieved significant success in various natural language processing tasks, including Question-Answering (QA) and dialogue systems. However, most models are trained on English data and lack strong generalization in providing answers in Chinese. This limitation is especially evident in specialized domains like traditional Chinese medical QA, where performance suffers due to the absence of fine-tuning and high-quality datasets. To address this, we introduce MedChatZH, a dialogue model optimized for Chinese medical QA based on transformer decoder with LLaMA architecture. Continued pre-training on a curated corpus of Chinese medical books is followed by fine-tuning with a carefully selected medical instruction dataset, resulting in MedChatZH outperforming several Chinese dialogue baselines on a real-world medical dialogue dataset. Our model, code, and dataset are publicly available on GitHub (https://github.com/tyang816/MedChatZH) to encourage further research in traditional Chinese medicine and LLMs.

KGSCS—a smart care system for elderly with geriatric chronic diseases: a knowledge graph approach

BackgroundThe increasing aging population has led to a shortage of geriatric chronic disease caregiver, resulting in inadequate care for elderly people. In this global context, many older people rely on nonprofessional family care. The credibility of existing health websites cannot meet the needs of care. Specialized health knowledge bases such as SNOMED—CT and UMLS are also difficult for nonprofessionals to use. Furthermore, professional caregiver in elderly care institutions also face difficulty caring for multiple elderly people at the same time and working handovers. As a solution, we propose a smart care system for the elderly based on a knowledge graph.MethodFirst, we worked with professional caregivers to design a structured questionnaire to collect more than 100 pieces of care-related information for the elderly. Then, in the proposed system, personal information, smart device data, medical knowledge, and nursing knowledge are collected and organized into a dynamic knowledge graph. The system offers report generation, question answering, risk identification and data updating services. To evaluate the effectiveness of the system, we use the expert evaluation method to score the user experience.ResultsThe results of the study showed that compared to existing tools (health websites, archives and expert team consultation), the system achieved a score of 8 or more for basic information, health support and Dietary information. Some secondary evaluation indicators reached 9 and 10 points. This finding suggested that the system is superior to existing tools. We also present a case study to help the reader understand the role of the system.ConclusionThe smart care system provide personalized care guidelines for nonprofessional caregivers. It also makes the job easier for institutional caregivers. In addition, the system provides great convenience for work handover.

Leveraging Text-to-Text Pretrained Language Models for Question Answering in Chemistry.

In this study, we present a question answering (QA) system for chemistry, named Marie, with the use of a text-to-text pretrained language model to attain accurate data retrieval. The underlying data store is "The World Avatar" (TWA), a general world model consisting of a knowledge graph that evolves over time. TWA includes information about chemical species such as their chemical and physical properties, applications, and chemical classifications. Building upon our previous work on KGQA for chemistry, this advanced version of Marie leverages a fine-tuned Flan-T5 model to seamlessly translate natural language questions into SPARQL queries with no separate components for entity and relation linking. The developed QA system demonstrates competence in providing accurate results for complex queries that involve many relation hops as well as showcasing the ability to balance correctness and speed for real-world usage. This new approach offers significant advantages over the prior implementation that relied on knowledge graph embedding. Specifically, the updated system boasts high accuracy and great flexibility in accommodating changes and evolution of the data stored in the knowledge graph without necessitating retraining. Our evaluation results underscore the efficacy of the improved system, highlighting its superior accuracy and the ability in answering complex questions compared to its predecessor.

Data Quality of Different Modes of Supervision in Classroom Surveys

Conducting quantitative research involving adolescents demands a thoughtful approach to the question of supervision, given that each option comes with its distinct set of implications. This study reviews these implications and empirically tests whether differences in data quality can be found among three modes of standardized survey research with medium-sized groups of adolescents (12–17 years). The data basis is a quasi-experimental survey study testing different forms of digital, hybrid, or in-person supervision that took place in 2021 in secondary schools in Germany (N = 923). The aim of this study is to test how aspects of data quality—item nonresponse, interview duration, drop-out rate, and response patterns—differ between these forms of supervision. Results could help researchers surveying young people to decide (1) whether they allow confidants or other adults to be present during interviews, (2) if they can rely on teachers alone when surveying classrooms, and (3) if it is cost-efficient to send out external supervisors for classroom sessions. While drop-out rates do not differ, item non-response, interview duration, and response patterns differ significantly; students supervised at home by external interviewers answered more questions, took more time to answer, and were less likely to give potentially meaningless answers in grid questions. The implications drawn from the findings question the common approach of solely relying on teachers for survey administration without the support of external supervisors or adequate training. Recruiting respondents via schools and surveying them online in their homes during school hours has been shown to be a robust method with regard to the analyzed indicators.

Benchmarks for Pirá 2.0, a Reading Comprehension Dataset about the Ocean, the Brazilian Coast, and Climate Change

ABSTRACT Pirá is a reading comprehension dataset focused on the ocean, the Brazilian coast, and climate change, built from a collection of scientific abstracts and reports on these topics. This dataset represents a versatile language resource, particularly useful for testing the ability of current machine learning models to acquire expert scientific knowledge. Despite its potential, a detailed set of baselines has not yet been developed for Pirá. By creating these baselines, researchers can more easily utilize Pirá as a resource for testing machine learning models across a wide range of question answering tasks. In this paper, we define six benchmarks over the Pirá dataset, covering closed generative question answering, machine reading comprehension, information retrieval, open question answering, answer triggering, and multiple choice question answering. As part of this effort, we have also produced a curated version of the original dataset, where we fixed a number of grammar issues, repetitions, and other shortcomings. Furthermore, the dataset has been extended in several new directions, so as to face the aforementioned benchmarks: translation of supporting texts from English into Portuguese, classification labels for answerability, automatic paraphrases of questions and answers, and multiple choice candidates. The results described in this paper provide several points of reference for researchers interested in exploring the challenges provided by the Pirá dataset.

Transformer-based vision-language alignment for robot navigation and question answering

The task of robot navigation and question answering, which is also known as Embodied Question Answering (EQA), places its emphasis on empowering agents to actively explore their environments and deliver answers to user inquiries. Considering the extensive range of potential applications, particularly in the realms of home robots and personal assistants, the Embodied Question Answering task has attracted growing attention from researchers. Owing to the difficulties in bridging the semantic divide between inputs from different modalities and capturing extended connections between widely separated pixels, most existing methods face challenges in attaining adequate performance concerning accuracy in navigation and responses. To address these challenges, we present a transformer-based framework that aligns vision and language information for the task of robot navigation and question answering. Firstly, an information fusion model is designed to utilize object tags as reference points for aligning the vision and linguistic modalities into a coherent semantic space. Secondly, a dedicated transformer block is employed to capture extensive dependencies within visual scenes, enabling the generation of more contextually appropriate actions. Lastly, the two transformer-based components are seamlessly integrated into a cohesive framework, effectively handling the complete Embodied Question Answering task. The results of our experiments clearly indicate that our approach substantially boosts the performance of every module in the system, resulting in a notable 4.1% enhancement in overall accuracy.

Applying a Context-based Method to Build a Knowledge Graph for the Blue Amazon

ABSTRACT Knowledge graphs are employed in several tasks, such as question answering and recommendation systems, due to their ability to represent relationships between concepts. Automatically constructing such a graphs, however, remains an unresolved challenge within knowledge representation. To tackle this challenge, we propose CtxKG, a method specifically aimed at extracting knowledge graphs in a context of limited resources in which the only input is a set of unstructured text documents. CtxKG is based on OpenIE (a relationship triple extraction method) and BERT (a language model) and contains four stages: the extraction of relationship triples directly from text; the identification of synonyms across triples; the merging of similar entities; and the building of bridges between knowledge graphs of different documents. Our method distinguishes itself from those in the current literature (i) through its use of the parse tree to avoid the overlapping entities produced by base implementations of OpenIE; and (ii) through its bridges, which create a connected network of graphs, overcoming a limitation similar methods have of one isolated graph per document. We compare our method to two others by generating graphs for movie articles from Wikipedia and contrasting them with benchmark graphs built from the OMDb movie database. Our results suggest that our method is able to improve multiple aspects of knowledge graph construction. They also highlight the critical role that triple identification and named-entity recognition have in improving the quality of automatically generated graphs, suggesting future paths for investigation. Finally, we apply CtxKG to build BlabKG, a knowledge graph for the Blue Amazon, and discuss possible improvements.

Evaluating ChatGPT ability to answer urinary tract Infection-Related questions

IntroductionFor the first time, the accuracy and proficiency of ChatGPT answers on urogenital tract infection (UTIs) were evaluated. MethodsThe study aimed to create two lists of questions: frequently asked questions (FAQs, public-based inquiries) on relevant topics, and questions based on guideline information (guideline-based inquiries). ChatGPT responses to FAQs and scientific questions were scored by two urologists and an infectious disease specialist. Quality and reliability of all ChatGPT answers were checked using the Global Quality Score (GQS). The reproducibility of ChatGPT answers was analyzed by asking each question twice. ResultsAll in all, 96.2 % of FAQs (75/78 inquiries) related to UTIs were correctly and adequately answered by ChatGPT, and scored GQS 5. None of the ChatGPT answers were classified as GQS 2 and GQS 1. Moreover, FAQs about cystitis, urethritis, and epididymo-orchitis were answered by ChatGPT with 100 % accuracy (GQS 5). ChatGPT answers for EAU urological infections guidelines showed that 61 (89.7 %), 5 (7.4 %), and 2 (2.9 %) ChatGPT responses were scored GQS 5, GQS 4, and GQS 3, respectively. None of the ChatGPT responses for EAU urological infections guidelines were categorized as GQS 2 and GQS 1. Comparison of mean GQS values of ChatGPT answers for FAQs and EAU urological guideline questions showed that ChatGPT was similarly able to respond to both question groups (p = 0.168). The ChatGPT response reproducibility rate was highest for the FAQ subgroups of cystitis, urethritis, and epididymo-orchitis (100 % for each subgroup). ConclusionThe present study showed that ChatGPT gave accurate and satisfactory answers for both public-based inquiries, and EAU urological infection guideline-based questions. Reproducibility of ChatGPT answers exceeded 90% for both FAQs and scientific questions.

An action-specific examination of the role of answerers’ gaze orientation in managing transition relevance

ABSTRACT We use conversation analysis to both qualitatively and quantitatively demonstrate that, in a specific action context, an answerer’s gaze orientation at the end of their answer’s first verbal turn-constructional unit (TCU) is one cooperating element of a multi-resource gestalt for managing the answer-turn’s transition relevance. Specifically, gazing at (vs. away from) a questioner claims that the initial TCU is (or is not yet) transition-relevant. Findings suggest that an additional resource is prior context in the form of the amount of delay (in milliseconds) of an answer relative to its question. Other potential resources, such as the TCU’s type conformity generally and its specific status as a “Yes”- or “No”-type answer, were not associated with transition relevance. Data are 274 polar, question–answer sequences—representing the very delimited social action of relatively genuine information-seeking—drawn from videotapes of completely unstructured, face-to-face interactions between dyads of native English-speaking, adult close friends.

ZVQAF: Zero-shot visual question answering with feedback from large language models

Due to the prominent zero-shot generalization in new language tasks shown by large language models (LLMs), applying LLMs for zero-shot visual question answering (VQA) has been a new trend. However, most prior approaches directly use off-the-shelf captioning models to generate captions that compose in-context examples for LLMs, and such generated captions may be uninformative, thus leading the LLMs to give false predictions. To address this, we propose zero-shot VQA with feedback from LLMs (ZVQAF), a framework that applies LLMs to discriminate the quality of generated captions and leverages this feedback to train the captioning model. ZVQAF consists of two stages: the first stage is the training with feedback, which enables the captioning model to recognize the task objective and information requirements from the LLM, and the second stage is utilizing the optimized captioning model and LLM for inference. Extensive experiments show that ZVQAF achieves zero-shot VQA performance that is comparable or even superior to those previous zero-shot, few-shot, and end-to-end training approaches. For example, on VQAv2 test dataset, ZVQAF outperforms Flamingo (Alayrac et al., 2022) which employs end-to-end training by a large margin of 8.0%. In addition, on A-OKVQA dataset, ZVQAF outperforms zero-shot method Img2LLM (Guo et al., 2023) by 3.8% when employing LLMs with similar scales.

Prompting large language model with context and pre-answer for knowledge-based VQA

Existing studies apply Large Language Model (LLM) to knowledge-based Visual Question Answering (VQA) with encouraging results. Due to the insufficient input information, the previous methods still have shortcomings in constructing the prompt for LLM, and cannot fully activate the capacity of LLM. In addition, previous works adopt GPT-3 for inference, which has expensive costs. In this paper, we propose PCPA: a framework that Prompts LLM with Context and Pre-Answer for VQA. Specifically, we adopt a vanilla VQA model to generate in-context examples and candidate answers, and add a pre-answer selection layer to generate pre-answers. We integrate in-context examples and pre-answers into the prompt to inspire the LLM. In addition, we choose LLaMA instead of GPT-3, which is an open and free model. We build a small dataset to fine-tune the LLM. Compared to existing baselines, the PCPA improves accuracy by more than 2.1 and 1.5 on OK-VQA and A-OKVQA, respectively.