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 23 for “"Long Documents"”.

  1. Graph-based extractive summarisation for long documents

    … to extract the most important information from a longer document or a collection of documents quickly and accurately has always been essential for effective communication and decision-making. By leveraging text summarisation systems, this process can be facilitated more efficiently. Text …

    birmingham Download PDF for Graph-based extractive summarisation for long documents (opens in a new tab)

  2. Toward Entity-Centric Understanding of Long Documents

    … biographies, legal contracts, or narratives. Documents such as legal contracts and narratives are centered around people entities containing rich information about them (such as the rights and duties of the contracting parties, or emotional states of characters in a book), the events they …

    maryland Repository record for Toward Entity-Centric Understanding of Long Documents (opens in a new tab)

  3. Multimodal understanding of long documents : from topic modeling to question answering

    Long multimodal documents, which contain text, images, and other types of content, are common in real-world settings but remain difficult for natural language processing (NLP) models to process. These documents pose challenges in both understanding their content and training models when labeled …

    ubc Repository record for Multimodal understanding of long documents : from topic modeling to question answering (opens in a new tab) Download PDF for Multimodal understanding of long documents : from topic modeling to question answering (opens in a new tab)

  4. Extractive summarization of long documents by combining global and local context

    … extractive summarization model for long documents, incorporating both the global context of the whole document and the local context within the current topic. We evaluate the model on two datasets of scientific papers , Pubmed and arXiv, where it outperforms previous work, both …

    ubc Repository record for Extractive summarization of long documents by combining global and local context (opens in a new tab) Download PDF for Extractive summarization of long documents by combining global and local context (opens in a new tab)

  5. IMPROVING REVISITATION IN LONG DOCUMENTS WITH TWO-LEVEL ARTIFICIAL-LANDMARK SCROLLBARS

    … document and allow effective navigation in short documents, they are not effective in long documents, particularly for revisitation. Bookmarks, search and history dialogs, and “read wear” (visual marks left as the user interacts with the document) can all assist revisitation; however, for long …

    sask Repository record for IMPROVING REVISITATION IN LONG DOCUMENTS WITH TWO-LEVEL ARTIFICIAL-LANDMARK SCROLLBARS (opens in a new tab)

  6. RingChains Graph-based Summarizer and Enhanced Large Language Models for Summarizing Long Documents

    … for LLMs to perform the summary task for long documents. First, LLMs must compute a large number of unimportant input tokens while LLMs perform more than billions operations per an input token because of the complicated architecture and large model sizes. Second, most standard LLMs have a …

    unt Repository record for RingChains Graph-based Summarizer and Enhanced Large Language Models for Summarizing Long Documents (opens in a new tab)

  7. Scholarly Information System for Long Documents and their Elements: Structured Representation and Exploration using Knowledge Graphs and LLMs

    Every year, thousands of students write long and detailed theses and dissertations as part of their graduate requirement. These documents contain valuable knowledge—methods, explanations, figures, and insights—but because they are so long, it is often difficult for researchers to find exactly what …

    vt Repository record for Scholarly Information System for Long Documents and their Elements: Structured Representation and Exploration using Knowledge Graphs and LLMs (opens in a new tab)

  8. Enhancing Layout Understanding via Human-in-the-Loop: A User Study on PDF-to-HTML Conversion for Long Documents

    … document elements, enabling systems that convert documents into searchable and editable formats to enhance accessibility and usability. Nevertheless, the recognition results often contain errors that require manual correction due to small training dataset size, limitations of models, and defects …

    vt Repository record for Enhancing Layout Understanding via Human-in-the-Loop: A User Study on PDF-to-HTML Conversion for Long Documents (opens in a new tab)

  9. Segmenting Electronic Theses and Dissertations By Chapters

    … many services. Some of these include summarizing long documents, semantic parsing, classification, and indexing for discovery. This thesis puts forward a bottom-up approach to segmenting ETDs and shows that LaTeX manipulation can be used to help create meaningful data sets. The research provides …

    vt Repository record for Segmenting Electronic Theses and Dissertations By Chapters (opens in a new tab)

  10. Multi-document summarization based on document clustering and neural sentence fusion

    … and the inaccuracy in representing multiple long documents into a fixed size vector inspired us to design complementary models for two different tasks such as sentence clustering and neural sentence fusion. In this thesis, we minimize the risk of producing incorrect fact by encoding a related …

    lethbridge Repository record for Multi-document summarization based on document clustering and neural sentence fusion (opens in a new tab)

  11. Evaluating a Joint Neural Model with Global Features for Document-Level End-to-End Information Extraction

    … IE dataset is needed for research on processing long documents. Fortunately, researchers at Allen Institute for AI published a comprehensive and challenging document-level IE dataset (SCIREX) for the IE research community to study. Performing end-to-end IE tasks on SCIREX requires global …

    oregon Repository record for Evaluating a Joint Neural Model with Global Features for Document-Level End-to-End Information Extraction (opens in a new tab)

  12. Information Extraction of Technical Details From Scholarly Articles

    … progress in information extraction from short documents in the last few years, including social media interaction, news articles, and email excerpts. This research aims to extract technical entities like hardware resources, computing platforms, compute time, programming language, and libraries …

    vt Repository record for Information Extraction of Technical Details From Scholarly Articles (opens in a new tab)

  13. Entity-based long document summarization using LLMs

    Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2026-05-01

    uiuc Repository record for Entity-based long document summarization using LLMs (opens in a new tab)

  14. ResearchBuddy AI: LLM-Powered Assistant

    … question answering over domain-specific documents. The research explains model selection through self-hosted open-source models with LoRA (Low Rank Adaptation) and other techniques to achieve cost-effectiveness and control. The research paper summarization capability was developed through …

    texas-state Repository record for ResearchBuddy AI: LLM-Powered Assistant (opens in a new tab)

  15. Neural Document Segmentation Using Weighted Sliding Windows with Transformer Encoders

    The subdivision of documents into semantically coherent segments is a fundamental challenge in Natural Language Processing (NLP), with notable applications in information retrieval and question answering. Effective text segmentation is crucial for enhancing Retrieval-Augmented Generation (RAG) …

    york Repository record for Neural Document Segmentation Using Weighted Sliding Windows with Transformer Encoders (opens in a new tab)

  16. Investigating the Extractive Summarization of Literary Novels

    … Given that a large fraction of the electronic documents available online and elsewhere consist of short texts such as Web pages, news articles, scientific reports, and others, the focus of natural language processing techniques to date has been on the automation of methods targeting short …

    unt Repository record for Investigating the Extractive Summarization of Literary Novels (opens in a new tab)

  17. Efficient Long-Context Retrieval Systems via Dynamic Sparse Attention

    Large language models now admit inputs far longer than a single query, so a model can reason jointly over whole collections of long documents. Context windows are finite, however, and so retrieval-augmented generation (RAG) closes that gap by indexing the corpus and retrieving the relevant evidence …

    ethz Repository record for Efficient Long-Context Retrieval Systems via Dynamic Sparse Attention (opens in a new tab)

  18. Continuous Authentication using Stylometry

    … techniques can achieve high accuracy rates for long documents, it is still challenging to identify an author for short documents, in particular when dealing with large author populations. In this dissertation, we propose a new framework for continuous authentication using authorship verification …

    uvic Repository record for Continuous Authentication using Stylometry (opens in a new tab)

  19. Learning from Multimodal Web Data

    … grounded image-text relationships from noisy, long documents, e.g., Wikipedia articles and the images they contain. We also demonstrate that noisy web signals, such as speech recognition tokens from user-generated web videos, can be leveraged to improve performance in caption generation tasks. …

    cornell Repository record for Learning from Multimodal Web Data (opens in a new tab)

  20. Improving the effectiveness of language modeling approaches to information retrieval: bridging the theory-effectiveness gap

    … of general retrieval models has been a long-standing difficult challenge in information retrieval research, yet is also a fundamentally important task, because an improved general retrieval model would benefit every search engine. The language modeling approach to information retrieval …

    uiuc Repository record for Improving the effectiveness of language modeling approaches to information retrieval: bridging the theory-effectiveness gap (opens in a new tab)

Page 1 of 2