Corpus ID: 6026194

Optimizing Sentence Modeling and Selection for Document Summarization

@inproceedings{Yin2015OptimizingSM,
  title={Optimizing Sentence Modeling and Selection for Document Summarization},
  author={Wenpeng Yin and Yulong Pei},
  booktitle={IJCAI},
  year={2015}
}
Extractive document summarization aims to conclude given documents by extracting some salient sentences. Often, it faces two challenges: 1) how to model the information redundancy among candidate sentences; 2) how to select the most appropriate sentences. This paper attempts to build a strong summarizer DivSelect+CNNLM by presenting new algorithms to optimize each of them. Concretely, it proposes CNNLM, a novel neural network language model (NNLM) based on convolutional neural network (CNN), to… Expand
A Supervised Method for Extractive Single Document Summarization based on Sentence Embeddings and Neural Networks
TLDR
A deep neural network model based-method for extractive single document summarization using the state-of-the-art sentence embedding models is proposed and results show that this method outperforms eight well-known ATS baselines and achieves comparable results to the state of theart deep learning based methods. Expand
Deep reinforcement learning for extractive document summarization
Abstract We present a novel extractive document summarization approach based on a Deep Q-Network (DQN), which can model salience and redundancy of sentences in the Q-value approximation and learn aExpand
About ? Extreme Summarization with Topic-Aware Convolutional Neural Networks
We introduce extreme summarization, a new single-document summarization task which aims at creating a short, one-sentence news summary answering the question “What is the article about?”. We argueExpand
Classify or Select: Neural Architectures for Extractive Document Summarization
TLDR
Two novel and contrasting Recurrent Neural Network (RNN) based architectures for extractive summarization of documents are presented and the models under both architectures jointly capture the notions of salience and redundancy of sentences. Expand
Improving Neural Abstractive Document Summarization with Explicit Information Selection Modeling
TLDR
Experimental results demonstrate that the explicit modeling and optimizing of the information selection process improves document summarization performance significantly, which enables the model to generate more informative and concise summaries, and thus significantly outperform state-of-the-art neural abstractive methods. Expand
SummCoder: An unsupervised framework for extractive text summarization based on deep auto-encoders
TLDR
Empirical results show that the proposed SummCoder text summarization approach obtains comparable or better performance than the state-of-the-art methods for different ROUGE metrics. Expand
Sentence Relations for Extractive Summarization with Deep Neural Networks
TLDR
A deep neural network model, Sentence Relation-based Summarization (SRSum), that consists of five sub-models, PriorSum, CSRSum, TS RSum, QSRSums, and SFSum, that automatically learns useful latent features by jointly learning representations of query sentences, content sentences, and title sentences as well as their relations. Expand
Sharing Pre-trained BERT Decoder for a Hybrid Summarization
TLDR
This paper proposes a novel extractive-and-abstractive hybrid framework for single document summarization task by jointly learning to select sentence and rewrite summary and applies the BERT pre-trained model as document encoder, sharing the context representations to both decoders. Expand
EXTRACTIVE DOCUMENT SUMMARIZATION
We present two novel and contrasting Recurrent Neural Network (RNN) based architectures for extractive summarization of documents. The Classifier based architecture sequentially accepts or rejectsExpand
Extractive Summarization Using Multi-Task Learning with Document Classification
TLDR
A general framework for summarization that extracts sentences from a document using externally related information that is addressed in the framework of multi-task learning using curriculum learning for sentence extraction and document classification is proposed. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 47 REFERENCES
Automatic Multi-document Summarization Based on New Sentence Similarity Measures
TLDR
A general framework to exemplify how to combine the two factors above together so as to derive a corpus-oriented and more discriminative sentence similarity is presented. Expand
Towards an Iterative Reinforcement Approach for Simultaneous Document Summarization and Keyword Extraction
TLDR
A novel iterative reinforcement approach to simultaneously extractingsummary and keywords from single document under the assumption that the summary and keywords of a document can be mutually boosted. Expand
Unsupervised Approach for Selecting Sentences in Query-based Summarization
TLDR
This work extracted several features of different types for each of the sentences in the document collection in order to measure its relevancy to the user query and experimented with two well-known unsupervised statistical machine learning techniques: K-Means and EM algorithms and evaluated their performances. Expand
SentTopic-MultiRank: a Novel Ranking Model for Multi-Document Summarization
TLDR
SentTopic-MultiRank is proposed, a novel ranking model for multi-document summarization that assumes various topics to be heterogeneous relations, then treats sentence connections in multiple topics as a heterogeneous network, where sentences and topics/relations are effectively linked together. Expand
A Convolutional Neural Network for Modelling Sentences
TLDR
A convolutional architecture dubbed the Dynamic Convolutional Neural Network (DCNN) is described that is adopted for the semantic modelling of sentences and induces a feature graph over the sentence that is capable of explicitly capturing short and long-range relations. Expand
Multi-document summarization via sentence-level semantic analysis and symmetric matrix factorization
TLDR
A new multi-document summarization framework based on sentence-level semantic analysis and symmetric non-negative matrix factorization is proposed, which aims to create a compressed summary while retaining the main characteristics of the original set of documents. Expand
Document-Based HITS Model for Multi-document Summarization
TLDR
The document-based HITS model (DocHITS) is proposed to fully leverage the document-level information by considering documents and sentences as hubs and authorities and Experimental results on the DUC2001 and DUC2002 datasets demonstrate the good effectiveness of the model. Expand
A new sentence similarity measure and sentence based extractive technique for automatic text summarization
TLDR
The purpose of present paper is to show, that summarization result not only depends on optimized function, and also depends on a similarity measure. Expand
Distributed Representations of Sentences and Documents
TLDR
Paragraph Vector is an unsupervised algorithm that learns fixed-length feature representations from variable-length pieces of texts, such as sentences, paragraphs, and documents, and its construction gives the algorithm the potential to overcome the weaknesses of bag-of-words models. Expand
Generic Multi-Document Summarization Using Topic-Oriented Information
TLDR
The topic-oriented PageRank (ToPageRank) model, in which topic information is fully incorporated, and the topic- oriented HITS (ToHITS) model is designed to compare the influence of different graph-based algorithms are proposed. Expand
...
1
2
3
4
5
...