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 13 of 13 for “"Sentence compression"”.

  1. Syntactic Sentence Compression for Text Summarization

    … and coherent summaries. As a result of this, sentence simplification has become a prominent requirement in automatic summarization. This thesis presents our work on sentence compression using syntactic pruning methods in order to improve automatic text summarization. Sentence compression has …

    concordia Download PDF for Syntactic Sentence Compression for Text Summarization (opens in a new tab)

  2. Toward abstractive multi-document summarization using submodular function-based framework, sentence compression and merging

    … for each of them. In addition, we integrate sentence compression and sentence merging. When evaluated on the DUC 2004 data set, our generic summarizer has outperformed the state-of-the-art summarization systems in terms of ROUGE-1 recall and f1-measure. For query-focused summarization, we …

    lethbridge Repository record for Toward abstractive multi-document summarization using submodular function-based framework, sentence compression and merging (opens in a new tab)

  3. Abstractive multi-document summarization - paraphrasing and compressing with neural networks

    … and multiple documents.The focus is on using sentence paraphrasing and compression for generating fluent summaries, especially in multi-document summarization where there is data paucity. A novel solution is to use transfer-learning from downstream tasks with an abundance of data. For this …

    lethbridge Repository record for Abstractive multi-document summarization - paraphrasing and compressing with neural networks (opens in a new tab)

  4. Deep generative models for natural language processing

    … variable models</b>. Chapter 6 introduces latent sentence compression models. The Auto-encoding Sentence Compression Model (ASC), as a discrete variational auto-encoder, generates a sentence by a sequence of discrete latent variables representing explicit words. The Forced Attention Sentence …

    oxford Repository record for Deep generative models for natural language processing (opens in a new tab)

  5. Multiple Alternative Sentene Compressions as a Tool for Automatic Summarization Tasks

    … current systems summarize texts by selecting sentences with important content. The limitation of extraction at the sentence level is that highly relevant sentences may also contain non-relevant and redundant content. This thesis presents a novel framework for text summarization that addresses …

    maryland Repository record for Multiple Alternative Sentene Compressions as a Tool for Automatic Summarization Tasks (opens in a new tab)

  6. Complex question answering : minimizing the gaps and beyond

    … by simply extracting a single entity or a single sentence. For example, the question: “How was Japan affected by the earthquake?” suggests that the inquirer is looking for information in the context of a wider perspective. We call these “complex questions” and focus on the task of answering them …

    lethbridge Repository record for Complex question answering : minimizing the gaps and beyond (opens in a new tab)

  7. Methods of sentence extraction, abstraction and ordering for automatic text summarization

    … tasks. We implement a rank based extractive sentence selection algorithm. For ensuring a pure sentence abstraction, we propose several novel sentence abstraction techniques which jointly perform sentence compression, fusion, and paraphrasing at the sentence level. We also model abstractive …

    lethbridge Repository record for Methods of sentence extraction, abstraction and ordering for automatic text summarization (opens in a new tab)

  8. Citation Handling: Processing Citation Texts in Scientific Documents

    Citation sentences (sentences that cite other papers) play a key role in the summarization of scientific articles. However, a citation-based summarization system that depends on generic natural language processing components, such as parsers or sentence compressors, will perform poorly if those …

    maryland Repository record for Citation Handling: Processing Citation Texts in Scientific Documents (opens in a new tab)

  9. Learning Deep Models with Linguistically-Inspired Structure

    … the discrete, compositional nature of words and sentences leads to natural combinatorial representations such as trees, sequences, segments, or alignments, among others. It is no surprise that structured output models have been successful and popular in NLP applications since their inception. At …

    cornell Repository record for Learning Deep Models with Linguistically-Inspired Structure (opens in a new tab)

  10. Monolingual Sentence Rewriting as Machine Translation: Generation and Evaluation

    … we investigate approaches to paraphrasing entire sentences within the constraints of a given task, which we call monolingual sentence rewriting. We introduce a unified framework for monolingual sentence rewriting, and apply it to three representative tasks: sentence compression, text …

    jhu Repository record for Monolingual Sentence Rewriting as Machine Translation: Generation and Evaluation (opens in a new tab)

  11. Automatic generation of natural language summaries

    … generate summaries by initially extracting the sentences that are most relevant to the user's query from documents returned by an information retrieval engine. In this thesis, we present a new competitive sentence extraction method that assigns relevance scores to the sentences of the texts to …

    greece Repository record for Automatic generation of natural language summaries (opens in a new tab)

  12. Toward abstractive text summarization

    … adaptable, we propose a word graph-based multi-sentence compression approach for improving both informativity and grammaticality of summaries, which shows 44% error reduction over state-of-the-art systems. Then, we discuss adapting this approach into query-focused multi-document summarization, …

    unsw Repository record for Toward abstractive text summarization (opens in a new tab)

  13. Deep Learning Approaches to Text Simplification for English as Second Language (ESL) Readers

    … and evaluated. The first contribution was a sentence compression method that extracts key information from sentences. This approach significantly outperformed existing methods, achieving a processing speed more than 10 times faster than recurrent neural network-based methods while maintaining …

    anu Repository record for Deep Learning Approaches to Text Simplification for English as Second Language (ESL) Readers (opens in a new tab)