Systematically Exploring Redundancy Reduction in Summarizing Long
Documents
- URL: http://arxiv.org/abs/2012.00052v1
- Date: Mon, 30 Nov 2020 19:07:27 GMT
- Title: Systematically Exploring Redundancy Reduction in Summarizing Long
Documents
- Authors: Wen Xiao, Giuseppe Carenini
- Abstract summary: We explore and compare different ways to deal with redundancy when summarizing long documents.
In a series of experiments, we show that our proposed methods achieve the state-of-the-art with respect to ROUGE scores on two scientific paper datasets.
- Score: 6.812554384019158
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Our analysis of large summarization datasets indicates that redundancy is a
very serious problem when summarizing long documents. Yet, redundancy reduction
has not been thoroughly investigated in neural summarization. In this work, we
systematically explore and compare different ways to deal with redundancy when
summarizing long documents. Specifically, we organize the existing methods into
categories based on when and how the redundancy is considered. Then, in the
context of these categories, we propose three additional methods balancing
non-redundancy and importance in a general and flexible way. In a series of
experiments, we show that our proposed methods achieve the state-of-the-art
with respect to ROUGE scores on two scientific paper datasets, Pubmed and
arXiv, while reducing redundancy significantly.
Related papers
- Unsupervised Multi-document Summarization with Holistic Inference [41.58777650517525]
This paper proposes a new holistic framework for unsupervised multi-document extractive summarization.
Subset Representative Index (SRI) balances the importance and diversity of a subset of sentences from the source documents.
Our findings suggest that diversity is essential for improving multi-document summary performance.
arXiv Detail & Related papers (2023-09-08T02:56:30Z) - Fine-Grained Distillation for Long Document Retrieval [86.39802110609062]
Long document retrieval aims to fetch query-relevant documents from a large-scale collection.
Knowledge distillation has become de facto to improve a retriever by mimicking a heterogeneous yet powerful cross-encoder.
We propose a new learning framework, fine-grained distillation (FGD), for long-document retrievers.
arXiv Detail & Related papers (2022-12-20T17:00:36Z) - ReSel: N-ary Relation Extraction from Scientific Text and Tables by
Learning to Retrieve and Select [53.071352033539526]
We study the problem of extracting N-ary relations from scientific articles.
Our proposed method ReSel decomposes this task into a two-stage procedure.
Our experiments on three scientific information extraction datasets show that ReSel outperforms state-of-the-art baselines significantly.
arXiv Detail & Related papers (2022-10-26T02:28:02Z) - On the Trade-off between Redundancy and Local Coherence in Summarization [20.16107829497668]
We investigate the trade-offs incurred when aiming to control for inter-sentential cohesion and redundancy in extracted summaries.
We find that the proposed unsupervised systems manage to extract highly cohesive summaries across varying levels of document redundancy.
arXiv Detail & Related papers (2022-05-20T14:10:28Z) - GERE: Generative Evidence Retrieval for Fact Verification [57.78768817972026]
We propose GERE, the first system that retrieves evidences in a generative fashion.
The experimental results on the FEVER dataset show that GERE achieves significant improvements over the state-of-the-art baselines.
arXiv Detail & Related papers (2022-04-12T03:49:35Z) - Augmenting Document Representations for Dense Retrieval with
Interpolation and Perturbation [49.940525611640346]
Document Augmentation for dense Retrieval (DAR) framework augments the representations of documents with their Dense Augmentation and perturbations.
We validate the performance of DAR on retrieval tasks with two benchmark datasets, showing that the proposed DAR significantly outperforms relevant baselines on the dense retrieval of both the labeled and unlabeled documents.
arXiv Detail & Related papers (2022-03-15T09:07:38Z) - On Generating Extended Summaries of Long Documents [16.149617108647707]
We present a new method for generating extended summaries of long papers.
Our method exploits hierarchical structure of the documents and incorporates it into an extractive summarization model.
Our analysis shows that our multi-tasking approach can adjust extraction probability distribution to the favor of summary-worthy sentences.
arXiv Detail & Related papers (2020-12-28T08:10:28Z) - WSL-DS: Weakly Supervised Learning with Distant Supervision for Query
Focused Multi-Document Abstractive Summarization [16.048329028104643]
In the Query Focused Multi-Document Summarization (QF-MDS) task, a set of documents and a query are given where the goal is to generate a summary from these documents.
One major challenge for this task is the lack of availability of labeled training datasets.
We propose a novel weakly supervised learning approach via utilizing distant supervision.
arXiv Detail & Related papers (2020-11-03T02:02:55Z) - SummPip: Unsupervised Multi-Document Summarization with Sentence Graph
Compression [61.97200991151141]
SummPip is an unsupervised method for multi-document summarization.
We convert the original documents to a sentence graph, taking both linguistic and deep representation into account.
We then apply spectral clustering to obtain multiple clusters of sentences, and finally compress each cluster to generate the final summary.
arXiv Detail & Related papers (2020-07-17T13:01:15Z) - Self-supervised Deep Reconstruction of Mixed Strip-shredded Text
Documents [63.41717168981103]
This work extends our previous deep learning method for single-page reconstruction to a more realistic/complex scenario.
In our approach, the compatibility evaluation is modeled as a two-class (valid or invalid) pattern recognition problem.
The proposed method outperforms the competing ones on complex scenarios, achieving accuracy superior to 90%.
arXiv Detail & Related papers (2020-07-01T21:48:05Z) - A Divide-and-Conquer Approach to the Summarization of Long Documents [4.863209463405628]
We present a novel divide-and-conquer method for the neural summarization of long documents.
Our method exploits the discourse structure of the document and uses sentence similarity to split the problem into smaller summarization problems.
We demonstrate that this approach paired with different summarization models, including sequence-to-sequence RNNs and Transformers, can lead to improved summarization performance.
arXiv Detail & Related papers (2020-04-13T20:38:49Z)
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.