Enhance Long Text Understanding via Distilled Gist Detector from Abstractive Summarization

• URL: http://arxiv.org/abs/2110.04741v1
• Date: Sun, 10 Oct 2021 09:21:24 GMT
• Title: Enhance Long Text Understanding via Distilled Gist Detector from Abstractive Summarization
• Authors: Yan Liu, Yazheng Yang
• Abstract summary: We consider the problem of how to disentangle the gist-relevant and irrelevant information for long text understanding. Experiments on document classification, distantly supervised open-domain question answering (DS-QA) and non-parallel text style transfer show that our method can significantly improve the performance of the baseline models.
• Score: 7.851265919027389
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Long text understanding is important yet challenging in natural language processing. A long article or essay usually contains many redundant words that are not pertinent to its gist and sometimes can be regarded as noise. In this paper, we consider the problem of how to disentangle the gist-relevant and irrelevant information for long text understanding. With distillation mechanism, we transfer the knowledge about how to focus the salient parts from the abstractive summarization model and further integrate the distilled model, named \emph{Gist Detector}, into existing models as a supplementary component to augment the long text understanding. Experiments on document classification, distantly supervised open-domain question answering (DS-QA) and non-parallel text style transfer show that our method can significantly improve the performance of the baseline models, and achieves state-of-the-art overall results for document classification.

Related papers

• Coarse-to-Fine Highlighting: Reducing Knowledge Hallucination in Large Language Models [58.952782707682815]
  COFT is a novel method to focus on different-level key texts, thereby avoiding getting lost in lengthy contexts. Experiments on the knowledge hallucination benchmark demonstrate the effectiveness of COFT, leading to a superior performance over $30%$ in the F1 score metric.
  arXiv  Detail & Related papers  (2024-10-19T13:59:48Z)
• Hypergraph based Understanding for Document Semantic Entity Recognition [65.84258776834524]
  We build a novel hypergraph attention document semantic entity recognition framework, HGA, which uses hypergraph attention to focus on entity boundaries and entity categories at the same time. Our results on FUNSD, CORD, XFUNDIE show that our method can effectively improve the performance of semantic entity recognition tasks.
  arXiv  Detail & Related papers  (2024-07-09T14:35:49Z)
• Improving Long Text Understanding with Knowledge Distilled from Summarization Model [17.39913210351487]
  We propose our emphGist Detector to leverage the gist detection ability of a summarization model. Gist Detector first learns the gist detection knowledge distilled from a summarization model, and then produces gist-aware representations. We evaluate our method on three different tasks: long document classification, distantly supervised open-domain question answering, and non-parallel text style transfer.
  arXiv  Detail & Related papers  (2024-05-08T10:49:39Z)
• Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedback [57.816210168909286]
  We leverage recent progress on textual entailment models to address this problem for abstractive summarization systems. We use reinforcement learning with reference-free, textual entailment rewards to optimize for factual consistency. Our results, according to both automatic metrics and human evaluation, show that our method considerably improves the faithfulness, salience, and conciseness of the generated summaries.
  arXiv  Detail & Related papers  (2023-05-31T21:04:04Z)
• Toward Unifying Text Segmentation and Long Document Summarization [31.084738269628748]
  We study the role that section segmentation plays in extractive summarization of written and spoken documents. Our approach learns robust sentence representations by performing summarization and segmentation simultaneously. Our findings suggest that the model can not only achieve state-of-the-art performance on publicly available benchmarks, but demonstrate better cross-genre transferability.
  arXiv  Detail & Related papers  (2022-10-28T22:07:10Z)
• Reinforcing Semantic-Symmetry for Document Summarization [15.113768658584979]
  Document summarization condenses a long document into a short version with salient information and accurate semantic descriptions. This paper introduces a new textbfreinforcing stextbfemantic-textbfsymmetry learning textbfmodel is proposed for document summarization. A series of experiments have been conducted on two wildly used benchmark datasets CNN/Daily Mail and BigPatent.
  arXiv  Detail & Related papers  (2021-12-14T17:41:37Z)
• Modular Self-Supervision for Document-Level Relation Extraction [17.039775384229355]
  We propose decomposing document-level relation extraction into relation detection and argument resolution. We conduct a thorough evaluation in biomedical machine reading for precision oncology, where cross-paragraph relation mentions are prevalent. Our method outperforms prior state of the art, such as multi-scale learning and graph neural networks, by over 20 absolute F1 points.
  arXiv  Detail & Related papers  (2021-09-11T20:09:18Z)
• BASS: Boosting Abstractive Summarization with Unified Semantic Graph [49.48925904426591]
  BASS is a framework for Boosting Abstractive Summarization based on a unified Semantic graph. A graph-based encoder-decoder model is proposed to improve both the document representation and summary generation process. Empirical results show that the proposed architecture brings substantial improvements for both long-document and multi-document summarization tasks.
  arXiv  Detail & Related papers  (2021-05-25T16:20:48Z)
• Enhancing Extractive Text Summarization with Topic-Aware Graph Neural Networks [21.379555672973975]
  This paper proposes a graph neural network (GNN)-based extractive summarization model. Our model integrates a joint neural topic model (NTM) to discover latent topics, which can provide document-level features for sentence selection. The experimental results demonstrate that our model achieves substantially state-of-the-art results on CNN/DM and NYT datasets.
  arXiv  Detail & Related papers  (2020-10-13T09:30:04Z)
• Recurrent Chunking Mechanisms for Long-Text Machine Reading Comprehension [59.80926970481975]
  We study machine reading comprehension (MRC) on long texts. A model takes as inputs a lengthy document and a question and then extracts a text span from the document as an answer. We propose to let a model learn to chunk in a more flexible way via reinforcement learning.
  arXiv  Detail & Related papers  (2020-05-16T18:08:58Z)
• Few-Shot Learning for Opinion Summarization [117.70510762845338]
  Opinion summarization is the automatic creation of text reflecting subjective information expressed in multiple documents. In this work, we show that even a handful of summaries is sufficient to bootstrap generation of the summary text. Our approach substantially outperforms previous extractive and abstractive methods in automatic and human evaluation.
  arXiv  Detail & Related papers  (2020-04-30T15:37:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.