Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 20 of 38 for “"question-answer pairs"”.

  1. Indirect supervision for relation extraction using question-answer pairs

    … attention has been brought to tackling question-answering (QA) tasks, user feedback or datasets of such tasks become more accessible. In this paper, we propose a novel framework, ReQuest, to leverage question-answer pairs as an indirect source of supervision for relation extraction, and …

    uiuc Repository record for Indirect supervision for relation extraction using question-answer pairs (opens in a new tab)

  2. Generating Canonical Sentences from Question-Answer Pairs of Deposition Transcripts

    … Deposition transcripts are in the form of question-answer (QA) pairs and can be quite lengthy for common people to read. This gives us a need to develop some automatic text-summarization method for the same. The present-day summarization systems do not support this form of text, entailing a …

    vt Repository record for Generating Canonical Sentences from Question-Answer Pairs of Deposition Transcripts (opens in a new tab)

  3. A Semantic Distance of Natural Language Queries Based on Question-Answer Pairs

    … techniques have been applied in the field of Question Answering (QA) for understanding natural language queries. Practical QA systems classify a natural language query into vertical domains, and determine whether it is similar to a question with known or latent answers. Current mobile personal …

    waterloo Repository record for A Semantic Distance of Natural Language Queries Based on Question-Answer Pairs (opens in a new tab)

  4. Interactive Question Answering Using Frame-Based Knowledge Representation

    A framework for building interactive question answering (IQA) systems is proposed based on a frame representation in dialogue systems. This method uses semantic role labeling for building a frame-based knowledge base (KB) from a dataset of question-answer pairs. A frame representation of a question …

    york Repository record for Interactive Question Answering Using Frame-Based Knowledge Representation (opens in a new tab)

  5. Building Blocks for Data-Driven Theories of Language Understanding

    … in natural language — in particular, using Question-Answer driven Semantic Role Labeling (QA-SRL), a simple schema for annotating verbal predicate-argument structure using highly constrained question-answer pairs. While this just scratches the surface of the complex language behaviors of …

    washington Repository record for Building Blocks for Data-Driven Theories of Language Understanding (opens in a new tab)

  6. An Investigation on Question Answering for an Online Feedable Chatbot

    … and implementation of a Chatbot that is able to answer questions about an entity it is learning about. This Chatbot is capable of automatically generating multiple genres using a unique technique to populate its SQL database from the Web. Our Online Feedable Chatbot can hold a conversation with …

    essex Download PDF for An Investigation on Question Answering for an Online Feedable Chatbot (opens in a new tab)

  7. AUTOMATIC ANNOTATION MANAGEMENT THROUGH DOCUMENT ENRICHMENT AND TRANSFER

    … documents. Q&A sites have a lot of high quality question-answer pairs. These contents can enrich the reading experiences of readers. For the second problem, it is resulted from the isolation of documents. We present a domination approach to link documents. When uploading a new document, …

    nus Repository record for AUTOMATIC ANNOTATION MANAGEMENT THROUGH DOCUMENT ENRICHMENT AND TRANSFER (opens in a new tab) Download file for AUTOMATIC ANNOTATION MANAGEMENT THROUGH DOCUMENT ENRICHMENT AND TRANSFER (opens in a new tab)

  8. KGScore-Open: Leveraging Knowledge Graph Semantics For Open-QA Evaluation

    Evaluating active Question Answering (QA) systems, as users ask questions outside of the original testing data, has proven to be difficult, due to the difficulty of gauging answer quality without ground truth responses. We propose KGScore-Open, a configurable system capable of scoring questions and …

    calpoly Repository record for KGScore-Open: Leveraging Knowledge Graph Semantics For Open-QA Evaluation (opens in a new tab)

  9. En AI-chattbot som förenklar arbetet för studievägledare

    … Given the focus on addressing frequently asked questions from students, the potential of fine-tuning a large language model was also explored. This was carried out through an automated pipeline that generated question–answer pairs for training purposes. The attempt at using fine-tuning did not …

    chalmers Repository record for En AI-chattbot som förenklar arbetet för studievägledare (opens in a new tab)

  10. Beyond single plots: A benchmark for question answering on scientific multi-charts

    … a large-scale dataset specifically designed for question answering over multi-chart figures. PolyChartQA comprises 534 multi-chart images (with a total of 2,297 sub-charts) sourced from peer-reviewed computer science research publications and 2,565 question-answer pairs annotated across diverse …

    iastate Repository record for Beyond single plots: A benchmark for question answering on scientific multi-charts (opens in a new tab)

  11. Designing for Trust in Chat-Based Question Answering Systems: An Exchange-Based Retrieval Approach

    … exchanges become buried, leading to repeated questions and sustained burden on experienced community members. This work contributes a set of design requirements for question-answering systems operating over unstructured chat data, a Discord bot prototype implementing those requirements named …

    calpoly Repository record for Designing for Trust in Chat-Based Question Answering Systems: An Exchange-Based Retrieval Approach (opens in a new tab)

  12. Large Multi-modal Model for Video Captioning

    … long caption evaluation into multiple short question-answer pairs. With the help of human Elo ranking, our experiments show that this benchmark better correlates with human judgments of video detailed captioning quality.

    washington Repository record for Large Multi-modal Model for Video Captioning (opens in a new tab)

  13. Towards agentic AI for point-of-care echocardiography reasoning and interpretation

    … benchmark of sonographer-veri ed clinical question-answer pairs and externally validated on a subset of MIMIC-IV-EchoQA. Ablation studies analyze tool contributions, error propagation, and the role of temporal video evidence. EchoAgent outperforms ultrasound-speci c and general medical …

    ubc Repository record for Towards agentic AI for point-of-care echocardiography reasoning and interpretation (opens in a new tab) Download PDF for Towards agentic AI for point-of-care echocardiography reasoning and interpretation (opens in a new tab)

  14. Incidental Supervision for Natural Language Understanding

    … we retrieve signals from sentence-level question-answer pairs to help NLU tasks via two types of sentence encoding approaches, depending on whether the target task involves single- or multi-sentence input. Second, we introduce a unified informativeness measure to quantitatively assess the …

    penn Repository record for Incidental Supervision for Natural Language Understanding (opens in a new tab)

  15. Resource-Efficient Machine Learning via Count-Sketches and Locality-Sensitive Hashing (LSH)

    … optimizer by efficiently training a synthetic question generator, which uses large-scale transformer networks to generate high-quality, human-readable question-answer pairs.

    rice Repository record for Resource-Efficient Machine Learning via Count-Sketches and Locality-Sensitive Hashing (LSH) (opens in a new tab)

  16. Improving Vulnerable Road Users' Safety Through Computer Vision-Based Crossing Direction Prediction And Multimodal Large Language Model-Based Accident Scene Description

    … accident videos with over 6,000 safety-critical question-answer pairs and 1,000 dense scene descriptions. This dataset supports systematic evaluation of MLLMs in accident-related video question answering and dense scene captioning, providing a critical resource for assessing safety-critical AI …

    ucf Repository record for Improving Vulnerable Road Users' Safety Through Computer Vision-Based Crossing Direction Prediction And Multimodal Large Language Model-Based Accident Scene Description (opens in a new tab)

  17. Closed Domain Question Answering With Language Models: Application of Retrieval-Augmented Generation and Parameter Efficient Fine-Tuning In Healthcare

    … by developing a framework for closed-domain Question Answering (QA) systems, with a focus on dementia care practices. The study employs a hybrid methodology combining Retrieval-Augmented Generation (RAG) with Parameter-Efficient Fine-Tuning (PEFT) to create a scalable, efficient, and …

    kennesaw Repository record for Closed Domain Question Answering With Language Models: Application of Retrieval-Augmented Generation and Parameter Efficient Fine-Tuning In Healthcare (opens in a new tab)

  18. QLoRaX: Heuristic-Guided Fine-Tuning of LLaMA-2 for Domain Adaptation in Entrepreneurship

    … dataset containing 3,545 human-written question-answer pairs, of which 3,095 were used for training and 450 were reserved for evaluation. A complete fine-tuning and evaluation pipeline was developed, which included clustering human-written answers, generating centroid-based summaries for …

    columbus-state Repository record for QLoRaX: Heuristic-Guided Fine-Tuning of LLaMA-2 for Domain Adaptation in Entrepreneurship (opens in a new tab)

  19. Pseudoclefts: A Self-Paced Reading Study Investigating Ellipsis Processing

    … argument for specificational pseudoclefts as question-answer pairs (QAP) places the burden of proof on any theory that does not posit a QAP analysis, (3) Hirsch (2017) arguements for the existence of VP-ellipsis in pseudoclefts. I then present an experiment that uses a self-paced reading task …

    mcmaster Repository record for Pseudoclefts: A Self-Paced Reading Study Investigating Ellipsis Processing (opens in a new tab)

  20. Experiments in neural question answering

    … methods to tackle the tasks of finding duplicate questions, learning to rank the answers of a Multiple Choice Question (MCQ) and classifying the answers to a question coming from the context of a paragraph. We draw our attention toward the problems related to sentence-sentence similarity. We used …

    lethbridge Repository record for Experiments in neural question answering (opens in a new tab)

Page 1 of 2