Extractive Summarization: Limits, Compression, Generalized Model and Heuristics

@article{Verma2017ExtractiveSL,
  title={Extractive Summarization: Limits, Compression, Generalized Model and Heuristics},
  author={Rakesh M. Verma and Daniel Lee},
  journal={Computaci{\'o}n y Sistemas},
  year={2017},
  volume={21}
}
Due to its promise to alleviate information overload, text summarization has attracted the attention of many researchers. However, it has remained a serious challenge. Here, we first prove empirical limits on the recall (and F1-scores) of extractive summarizers on the DUC datasets under ROUGE evaluation for both the single-document and multi-document summarization tasks. Next we define the concept of compressibility of a document and present a new model of summarization, which generalizes… Expand
Using Centroid Keywords and Word Mover's Distance for Single Document Extractive Summarization
TLDR
The main idea behind the method is in selecting sentences based on Word Mover's Distance Similarity between each sentence and set of centroid keywords, which leverages both compositional property of word embeddings and advantages of recently discovered powerful text to text distance metric. Expand
Abstractive Text Summarization using Seq2seq Model
TLDR
This paper presents an approach of abstractive text summarization using the seq2seq model and aims at enhancing the efficiency of the summary generated with the help of the data augmentation technique. Expand
Collection-Document Summaries
TLDR
The proposed criteria and procedure can be used to evaluate document-collection summaries without annotated corpora or provide additional insight in an evaluation with human-generated ground truth. Expand
LeafNATS: An Open-Source Toolkit and Live Demo System for Neural Abstractive Text Summarization
TLDR
This paper introduces an open-source toolkit, namely LeafNATS, for training and evaluation of different sequence-to-sequence based models for the NATS task, and for deploying the pre-trained models to real-world applications. Expand
Variational neural decoder for abstractive text summarization
TLDR
This paper proposes a variational neural decoder text summarization model (VND), which introduces a series of implicit variables by combining variational RNN and variational autoencoder, which is used to capture complex semantic representation at each step of decoding. Expand
DocEng'2020 Competition on Extractive Text Summarization
TLDR
The DocEng'2020 Competition on Extractive Text Summarization assessed the performance of six new methods and fourteen classical algorithms for extractive text sumarization using the CNN-Corpus, the largest test set available today for single document extractive summarization. Expand
Calculating the Upper Bounds for Multi-Document Summarization using Genetic Algorithms
TLDR
A method based on Genetic Algorithms is proposed for calculating the best sentence combinations of DUC01 and DUC02 datasets in MDS through a meta-document representation and three heuristics mentioned in several works of state-of-the-art are calculated to rank the most recent MDS methods. Expand
Ground Truth Spanish Automatic Extractive Text Summarization Bounds
TLDR
A standard corpus for Spanish EATS (SAETS) is created to evaluate the state-of-the-art methods and systems for the Spanish language and the first time that Jensen-Shannon divergence is used to evaluate AETS. Expand
RHETORICAL STRUCTURE THEORY AND ITS APPLICATION TO AUTOMATIC TEXT SUMMARIZATION.
TLDR
The Rhetorical Structure Theory and the possibility of using it to overcome the problem of how the resulting summaries aren’t always the most coherent are explored. Expand
A Comprehensive Attempt to Research Statement Generation
  • Wenhao Wu, Sujian Li
  • Computer Science
  • ArXiv
  • 2021
TLDR
A practical RSG method is proposed which identifies a researcher’s research directions by topic modeling and clustering techniques and extracts salient sentences by a neural text summarizer and outperforms all the baselines with better content coverage and coherence. Expand
...
1
2
...

References

SHOWING 1-10 OF 49 REFERENCES
Combining Syntax and Semantics for Automatic Extractive Single-Document Summarization
TLDR
The goal of this study is to reconsider the importance of single-document summarization by introducing a new approach and its implementation that essentially combines syntactic, semantic, and statistical methodologies, and reflects psychological findings that pinpoint specific selection patterns as humans construct summaries. Expand
Jointly Learning to Extract and Compress
TLDR
A joint model of sentence extraction and compression for multi-document summarization and its jointly extracted and compressed summaries outperform both unlearned baselines and the authors' learned extraction-only system on both ROUGE and Pyramid, without a drop in judged linguistic quality. Expand
Extractive Summarization under Strict Length Constraints
TLDR
A comparison of various techniques for single-document extractive summarization under strict length budgets shows that a supervised approach with lightweight and efficient features improves over the lead-based baseline, and performs competitively with a commercial system that uses more sophisticated features. Expand
Improving Multi-documents Summarization by Sentence Compression based on Expanded Constituent Parse Trees
TLDR
An innovative sentence compression method by considering every node in the constituent parse tree and deciding its status – remove or retain is proposed, which has similar ROUGE-2 scores but better linguistic quality on TAC data. Expand
Text Summarization Model Based on Maximum Coverage Problem and its Variant
TLDR
The augmented model is superior to the best-performing method of DUC'04 on ROUGE-1 without stopwords and augmenting the summarization model so that it takes into account the relevance to the document cluster. Expand
Automatic Text Summarization of Newswire: Lessons Learned from the Document Understanding Conference
TLDR
An overview of the achieved results in the different types of summarization tasks, comparing both the broader classes of baselines, systems and humans, as well as individual pairs of summarizers (both human and automatic). Expand
Fast and Robust Compressive Summarization with Dual Decomposition and Multi-Task Learning
TLDR
This work presents a dual decomposition framework for multi-document summarization, using a model that jointly extracts and compresses sentences, and proposes a multi-task learning framework to take advantage of existing data for extractive summarization and sentence compression. Expand
Extractive Summarization by Maximizing Semantic Volume
TLDR
This work embeds each sentence in a semantic space and construct a summary by choosing a subset of sentences whose convex hull maximizes volume in that space, and provides a greedy algorithm based on the GramSchmidt process to efficiently perform volume maximization. Expand
Topical Coherence for Graph-based Extractive Summarization
We present an approach for extractive single-document summarization. Our approach is based on a weighted graphical representation of documents obtained by topic modeling. We optimize importance,Expand
A Knowledge Induced Graph-Theoretical Model for Extract and Abstract Single Document Summarization
TLDR
This work introduces the graph theoretical model populated with semantic and statistical importance of terms, which helps in identifying the most representative and thematic facts in the document, and introduces the use of vertex constrained shortest path based technique, which uses minimum vertex cover related information as valuable resource to generate abstract summary. Expand
...
1
2
3
4
5
...