Answer To Question Research Articles

Improving ROUGE‐1 by 6%: A novel multilingual transformer for abstractive news summarization

SummaryNatural language processing (NLP) has undergone a significant transformation, evolving from manually crafted rules to powerful deep learning techniques such as transformers. These advancements have revolutionized various domains including summarization, question answering, and more. Statistical models like hidden Markov models (HMMs) and supervised learning have played crucial roles in laying the foundation for this progress. Recent breakthroughs in transfer learning and the emergence of large‐scale models like BERT and GPT have further pushed the boundaries of NLP research. However, news summarization remains a challenging task in NLP, often resulting in factual inaccuracies or the loss of the article's essence. In this study, we propose a novel approach to news summarization utilizing a fine‐tuned Transformer architecture pre‐trained on Google's mt‐small tokenizer. Our model demonstrates significant performance improvements over previous methods on the Inshorts English News dataset, achieving a 6% enhancement in the ROUGE‐1 score and reducing training loss by 50%. This breakthrough facilitates the generation of reliable and concise news summaries, thereby enhancing information accessibility and user experience. Additionally, we conduct a comprehensive evaluation of our model's performance using popular metrics such as ROUGE scores, with our proposed model achieving ROUGE‐1: 54.6130, ROUGE‐2: 31.1543, ROUGE‐L: 50.7709, and ROUGE‐LSum: 50.7907. Furthermore, we observe a substantial reduction in training and validation losses, underscoring the effectiveness of our proposed approach.

Image to Label to Answer: An Efficient Framework for Enhanced Clinical Applications in Medical Visual Question Answering

Medical Visual Question Answering (Med-VQA) faces significant limitations in application development due to sparse and challenging data acquisition. Existing approaches focus on multi-modal learning to equip models with medical image inference and natural language understanding, but this worsens data scarcity in Med-VQA, hindering clinical application and advancement. This paper proposes the ITLTA framework for Med-VQA, designed based on field requirements. ITLTA combines multi-label learning of medical images with the language understanding and reasoning capabilities of large language models (LLMs) to achieve zero-shot learning, meeting natural language module needs without end-to-end training. This approach reduces deployment costs and training data requirements, allowing LLMs to function as flexible, plug-and-play modules. To enhance multi-label classification accuracy, the framework uses external medical image data for pretraining, integrated with a joint feature and label attention mechanism. This configuration ensures robust performance and applicability, even with limited data. Additionally, the framework clarifies the decision-making process for visual labels and question prompts, enhancing the interpretability of Med-VQA. Validated on the VQA-Med 2019 dataset, our method demonstrates superior effectiveness compared to existing methods, confirming its outstanding performance for enhanced clinical applications.

Assessing Fine-Tuning Efficacy in LLMs: A Case Study with Learning Guidance Chatbots

Training and accurately evaluating task- specific chatbots is an important research area for Large Language Models (LLMs). These models can be developed for general purposes with the ability to handle multiple tasks, or fine-tuned for specific applications such as education or customer support. In this study, Mistral 7B, Llama-2 and Phi-2 models are utilized which have proven success on various benchmarks, including question answering. The models were fine-tuned using QLoRa with limited information gathered from course catalogs. The fine-tuned models were evaluated using various metrics, with the responses from GPT-4 taken as the ground truth. The experiments revealed that Phi-2 slightly outperformed Mistral 7B, achieving scores of 0.012 BLEU, 0.184 METEOR, and 0.873 BERT. Considering the evaluation metrics obtained, the strengths and weaknesses of known LLM models, the amount of data required for fine-tuning, and the effect of the fine-tuning method on model performance are discussed.

TPKE-QA: A gapless few-shot extractive question answering approach via task-aware post-training and knowledge enhancement

Few-shot extractive question answering (EQA) is a challenging task in natural language processing, whose current methods are mainly based on pretrained language models (PLMs). Data augmentation is often employed to improve the answer predictions of EQA models in few-shot settings. However, due to the differences between pretraining objectives and the EQA task, as well as embedding space alignment bottlenecks, the performance of few-shot EQA models must be improved. We propose TPKE-QA, a few-shot extractive Question Answering approach via Task-aware Post-training and Knowledge Enhancement, with entity-noun-oriented span selection in post-training, which can automatically generate EQA-style examples from a large-scale unlabeled corpus. By post-training based on generated examples, the gap between PLMs and the EQA task is effectively filled. To avoid embedding space alignment issues, a knowledge-enhanced sequence generation and knowledge injection approach for the EQA task enables gapless knowledge enhancement and fine-tuning on the post-trained model. In experiments, TPKE-QA achieved state-of-the-art results in most few-shot settings on the MRQA 2019 benchmark.

Malayalam Question Answering System Basedon a Deep Learning Hybrid Model of CNN andBi-LSTM Approach

Malayalam Question Answering System Basedon a Deep Learning Hybrid Model of CNN andBi-LSTM Approach

SExpSMA-based T5: Serial exponential-slime mould algorithm based T5 model for question answer and distractor generation

Generally, multiple choice questions are an effective and extensive form used in standard tests in order to evaluate the learner’s skills and knowledge. Nonetheless, the multiple-choice question composition particularly the distractor construction is quite difficult. The distracters are needed to be both plausible and inappropriate and adequate to mystify the learners who did not master the information. Thus, the distractor generation emergence is important that can help several standard tests in an extensive range of domain. In this research, question-answer generation system is developed with a distractor model by developing an optimized T5 model. At first, BERT tokenization is used to pre-process the passage/context and question, which are given as the input to train the approach. Then, the question and answer generation is performed by utilizing the T5 approach that is trained by proposed Serial Exponential-Slime Mould approach (SExpSMA). Exponential weighted moving average is extended to Serial Exponential weighted moving average and incorporated in Slime Mould Algorithm (SMA) to propose SExpSMA. In addition, the proposed SExpSMA-based T5 model is employed to generate distractors for the questions. Eventually, experimentation analysis exhibits that proposed SExpSMA-based T5 model achieves better outcomes regarding the metrics, like ROUGE, BLEU, and METEOR with the values of 0.919, 0.918, 0.488, respectively.

Neural models for semantic analysis of handwritten document images

Semantic analysis of handwritten document images offers a wide range of practical application scenarios. A sequential combination of handwritten text recognition (HTR) and a task-specific natural language processing system offers an intuitive solution in this domain. However, this HTR-based approach suffers from the problem of error propagation. An HTR-free model, which avoids explicit text recognition and solves the task end-to-end, tackles this problem, but often produces poor results. A possible reason for this is that it does not incorporate largely pre-trained semantic word embeddings, which turn out to be one of the most powerful advantages in the textual domain. In this work, we propose an HTR-based and an HTR-free model and compare them on a variety of segmentation-based handwritten document image benchmarks including semantic word spotting, named entity recognition, and question answering. Furthermore, we propose a cross-modal knowledge distillation approach to integrate semantic knowledge from textually pre-trained word embeddings into HTR-free models. In a series of experiments, we investigate optimization strategies for robust semantic word image representation. We show that the incorporation of semantic knowledge is beneficial for HTR-free approaches in achieving state-of-the-art results on a variety of benchmarks.

BioInstruct: instruction tuning of large language models for biomedical natural language processing.

To enhance the performance of large language models (LLMs) in biomedical natural language processing (BioNLP) by introducing a domain-specific instruction dataset and examining its impact when combined with multi-task learning principles. We created the BioInstruct, comprising 25005 instructions to instruction-tune LLMs (LLaMA 1 and 2, 7B and 13B version). The instructions were created by prompting the GPT-4 language model with 3-seed samples randomly drawn from an 80 human curated instructions. We employed Low-Rank Adaptation (LoRA) for parameter-efficient fine-tuning. We then evaluated these instruction-tuned LLMs on several BioNLP tasks, which can be grouped into 3 major categories: question answering (QA), information extraction (IE), and text generation (GEN). We also examined whether categories (eg, QA, IE, and generation) of instructions impact model performance. Comparing with LLMs without instruction-tuned, our instruction-tuned LLMs demonstrated marked performance gains: 17.3% in QA on average accuracy metric, 5.7% in IE on average F1 metric, and 96% in Generation tasks on average GPT-4 score metric. Our 7B-parameter instruction-tuned LLaMA 1 model was competitive or even surpassed other LLMs in the biomedical domain that were also fine-tuned from LLaMA 1 with vast domain-specific data or a variety of tasks. Our results also show that the performance gain is significantly higher when instruction fine-tuning is conducted with closely related tasks. Our findings align with the observations of multi-task learning, suggesting the synergies between 2 tasks. The BioInstruct dataset serves as a valuable resource and instruction tuned LLMs lead to the best performing BioNLP applications.

Beyond chat-GPT: a BERT-AO approach to custom question answering system

Beyond chat-GPT: a BERT-AO approach to custom question answering system

Transformative Trends: A Comprehensive Review of Large Language Models (LLMs) in Healthcare

Recent years have witnessed notable progress in Language Model (LM) technology, especially with the introduction of Large Language Models (LLMs). With the use of complex neural networks and enormous volumes of data, these models—like the GPT (Generative Pre-trained Transformer) series—have completely changed the field of natural language processing. This study offers a thorough analysis of LLMs, examining their uses as well as the difficulties and moral issues that come with implementing LLMs in practical settings. Moreover, it investigates the wide range of uses of LLMs in many fields, such as question answering, drug discovery, language translation, and text production. By means of this review, we hope to offer ideas on future directions in this quickly developing field as well as insights into the state-of-the-art in LLM research today. Key Words: Large Language Models, LangChain, Natural language processing, GPT, ChatGPT, AI chatbots, Indirect Prompt Injection

AI Driven Chatbot Counsellor

Speech and written information are fundamental to human communication. As a result, the majority of spoken and textual communication takes place on digital platforms like Twitter, Facebook, and WhatsApp, among others. Our model employs dual recurrent neural networks (RNNs) to encode the information from text and audio sequences, as spoken language and sound constitute emotional discourse. The emotion class is then predicted by combining the data from the two sources. Due to the complexity of speech emotion recognition, models that use audio properties to generate powerful classifiers have become increasingly important. Completing sentences or crafting sentences from a given starting word is a major aspect of natural language processing. In a way, it shows if a machine is capable of human creativity and mental processes. In order to assist handle diverse phrase generation challenges, we use natural language processing to train the machine for certain tasks. This is especially useful for application situations such as machine translation, automatic question answering, and summary creation. At the moment, OpenAI GPT and BERT are the most widely used language models for text generation and prediction. The approaches based on handwritten instructions, patterns, or statistical methods have been quickly superseded by the latest developments in deep learning and artificial intelligence, such as end-to-end trainable neural networks. This research presents a novel approach to deep neural learning-based chatbot creation. This approach builds a multilayer neural network to analyse and learn from the data. Furthermore, we employ supplementary limitations on the generation model to generate the correct response, which is capable of discerning the context of the discussion, the user's mood, and the anticipated response. This enables us to provide customised counselling replies depending on customer feedback. Through this study, two new corpora will be used to train the OpenAI GPT model, which will then be used to generate articles and long sentences. Finally, a comparison study will be carried out. Concurrently, we will use the BERT model to complete the task of context-based intermediate word prediction. Keywords : Artificial Intelligence, Data Science, NLP, Deep Learning, Machine Learning, GPT, Generative AI, Speech Synthesis

Disentangled Retrieval and Reasoning for Implicit Question Answering.

To date, most of the existing open-domain question answering (QA) methods focus on explicit questions where the reasoning steps are mentioned explicitly in the question. In this article, we study implicit QA where the reasoning steps are not evident in the question. Implicit QA is challenging in two aspects. First, evidence retrieval is difficult since there is little overlap between a question and its required evidence. Second, answer inference is difficult since the reasoning strategy is latent in the question. To tackle implicit QA, we propose a systematic solution denoted as DisentangledQA, which disentangles topic, attribute, and reasoning strategy from the implicit question to guide the retrieval and reasoning. Specifically, we disentangle the topic and attribute information from the implicit question to guide evidence retrieval. For answer reasoning, we propose a disentangled reasoning model for answer prediction based on retrieved evidence as well as the latent representation of the reasoning strategy. The disentangled framework empowers each module to focus on a specific latent element in the question, and thus, leads to effective representation learning for them. Experiments on the StrategyQA dataset demonstrate the effectiveness of our method in answering implicit questions, improving performance in evidence retrieval and answering inference by 31.7% and 4.5%, respectively, and achieving the best performance on the official leaderboard. In addition, our method achieved the best performance on the challenging EntityQuestions dataset, indicating the effectiveness in improving general open-domain QA tasks.

Evaluating LLMs on document-based QA: Exact answer selection and numerical extraction using CogTale dataset

Document-based Question-Answering (QA) tasks are crucial for precise information retrieval. While some existing work focus on evaluating large language model’s (LLMs) performance on retrieving and answering questions from documents, assessing the LLMs performance on QA types that require exact answer selection from predefined options and numerical extraction is yet to be fully assessed. In this paper, we specifically focus on this underexplored context and conduct empirical analysis of LLMs (GPT-4 and GPT-3.5) on question types, including single-choice, yes–no, multiple-choice, and number extraction questions from documents. We use the CogTale dataset for evaluation, which provide human expert-tagged responses, offering a robust benchmark for precision and factual grounding. We found that LLMs, particularly GPT-4, can precisely answer many single-choice and yes–no questions given relevant context, demonstrating their efficacy in information retrieval tasks. However, their performance diminishes when confronted with multiple-choice and number extraction formats, lowering the overall performance of the models on this task, indicating that these models may not yet be sufficiently reliable for the task. This limits the applications of LLMs on applications demanding precise information extraction and inference from documents, such as meta-analysis tasks. Our work offers a framework for ongoing dataset evaluation, ensuring that LLM applications for information retrieval and document analysis continue to meet evolving standards.

Bridging the Gap Between Information Seeking and Product Search Systems: Q&A Recommendation for E-Commerce

Consumers on a shopping mission often leverage both product search and information seeking systems, such as web search engines and Question Answering (QA) systems, in an iterative process to improve their understanding of available products and reach a purchase decision. While product search is useful for shoppers to find the actual products meeting their requirements in the catalog, information seeking systems can be utilized to answer any questions they may have to refine those requirements. The recent success of Large Language Models (LLMs) has opened up an opportunity to bridge the gap between the two tasks to help customers achieve their goals quickly and effectively by integrating conversational QA within product search. In this paper, we propose to recommend users Question-Answer (Q&A) pairs that are relevant to their product search and can help them make a purchase decision. We discuss the different aspects of the problem including the requirements and characteristics of the Q&A pairs, their generation, and the optimization of the Q&A recommendation task. We highlight the challenges, open problems, and suggested solutions to encourage future research in this emerging area.

Improve Question Classification Genetic Algorithm Based Feature Selection and Convolution Neural Network

Natural Language Processing (NLP) approaches play a crucial role in classifying inquiries and comprehending human language in diverse applications. A Question Answering System (QAS) consists of three components are question processing, information retrieval, and answer selection. Question Answering Systems (QASs) are a distinct form of information retrieval. The most crucial aspect of QAS is deciding on the question type since it influences the other sections following. However, an important question-answering system requires a prominent question classification system. In the past, there are different methods to solve this problem, such as rule-based learning, and hybrid approaches. However, the problem with these methods is that the rules require a lot of effort to create and are very limited. In this study, the utilization of genetic algorithm and deep neural network techniques enhances the quality control problem-solving process. This research utilizes the UIUC dataset. This collection comprises 5452 questions designed for learning purposes and an additional 500 questions specifically intended for assessment. The suggested solution involves converting each query into a matrix, with each row representing the Word2vec of a word. Subsequently, a Genetic Algorithm (GA) is employed to identify the most optimal features. Ultimately, a Convolutional Neural Network is utilized for classification, yielding a remarkable accuracy of 98.2% in our experimentation with the question dataset.

Question‐driven text summarization using an extractive‐abstractive framework

AbstractQuestion‐driven automatic text summarization is a popular technique to produce concise and informative answers to specific questions using a document collection. Both query‐based and question‐driven summarization may not produce reliable summaries nor contain relevant information if they do not take advantage of extractive and abstractive summarization mechanisms to improve performance. In this article, we propose a novel extractive and abstractive hybrid framework designed for question‐driven automatic text summarization. The framework consists of complimentary modules that work together to generate an effective summary: (1) discovering appropriate non‐redundant sentences as plausible answers using an open‐domain multi‐hop question answering system based on a convolutional neural network, multi‐head attention mechanism and reasoning process; and (2) a novel paraphrasing generative adversarial network model based on transformers rewrites the extracted sentences in an abstractive setup. Experiments show this framework results in more reliable abstractive summary than competing methods. We have performed extensive experiments on public datasets, and the results show our model can outperform many question‐driven and query‐based baseline methods (an R1, R2, RL increase of 6%–7% for over the next highest baseline).

Improving Topic Tracing with a Textual Reader for Conversational Knowledge Based Question Answering

Improving Topic Tracing with a Textual Reader for Conversational Knowledge Based Question Answering

Enhancing service excellence: analyzing natural language question answering with advanced cosine similarity

<span lang="EN-US">Information related to student services in higher education must be produced and disseminated in various forms. Covid-19 pandemic, student services with a remote model related to this question and answer become very important. To carry out this automation process, the advanced cosine similarity method is used to check the similarity of the questions to the database and statistics to calculate the similarity value of each word. The proposed paper proceeds with three phases. The first stage to solve this problem is the data processed in question; the professional next step is word insertion. It converts alphanumeric words to vector format. Each word is a vector that represents a point in space with a certain dimension. The recommended advanced cosine similarity data still must be analyzed into a statistical approach. We will measure accuracy to get results so that optimal results and answers are obtained, research procedures are carried out based on literature study, initial data collection and observation, system development, system testing, system analysis, and system evaluation. This research implemented in universities with student chat automation applications providing an accuracy 83.90% given by natural language question answering system (NLQAS) so that it can improve excellent service in universities.</span>

A multilingual semantic search chatbot framework

Chatbots are conversational agents which interact with users and simulate a human interaction. Companies use chatbots on their customer-facing sites to enhance user experience by answering questions about their products and directing users to relevant pages on the site. Existing Chatbots which are used for this purpose give responses based on pre-defined FAQs only. In this paper, we propose a framework for a chatbot which combines two approaches - retrieval from a knowledge base consisting of question answer pairs, combined with a natural language search mechanism which can scan through the paragraphs of text information. A feedback-based knowledge base update is implemented which provides continuous improvement in user experience. The framework achieves a result of 81.73 percent answer matching on SQuAD 1.1 and 69.21 percent answer matching on SQuAD 2.0. The framework also performs well on languages such as Spanish (67.32 percent answer match), Russian (61.43 percent answer match), Arabic (51.63 percent answer match) etc. by means of zero shot learning.

Cross-attention Based Text-image Transformer for Visual Question Answering

Background: Visual question answering (VQA) is a challenging task that requires multimodal reasoning and knowledge. The objective of VQA is to answer natural language questions based on corresponding present information in a given image. The challenge of VQA is to extract visual and textual features and pass them into a common space. However, the method faces the challenge of object detection being present in an image and finding the relationship between objects. Methods: In this study, we explored different methods of feature fusion for VQA, using pretrained models to encode the text and image features and then applying different attention mechanisms to fuse them. We evaluated our methods on the DAQUAR dataset. Results: We used three metrics to measure the performance of our methods: WUPS, Acc, and F1. We found that concatenating raw text and image features performs slightly better than selfattention for VQA. We also found that using text as query and image as key and value performs worse than other methods of cross-attention or self-attention for VQA because it might not capture the bidirectional interactions between the text and image modalities Conclusion: In this paper, we presented a comparative study of different feature fusion methods for VQA, using pre-trained models to encode the text and image features and then applying different attention mechanisms to fuse them. We showed that concatenating raw text and image features is a simple but effective method for VQA while using text as query and image as key and value is a suboptimal method for VQA. We also discussed the limitations and future directions of our work.