Topical Coherence for Graph-based Extractive Summarization

@inproceedings{Parveen2015TopicalCF,
  title={Topical Coherence for Graph-based Extractive Summarization},
  author={Daraksha Parveen and Hans-Martin Ramsl and M. Strube},
  booktitle={EMNLP},
  year={2015}
}
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, coherence and non-redundancy simultaneously using ILP. We compare ROUGE scores of our system with state-of-the-art results on scientific articles from PLOS Medicine and on DUC 2002 data. Human judges evaluate the coherence of summaries generated by our system in comparision to two baselines. Our… Expand
Extract with Order for Coherent Multi-Document Summarization
TLDR
A rank based sentence selection using continuous vector representations along with key-phrases is implemented and a model to tackle summary coherence for increasing readability is proposed. Expand
Generating Coherent Summaries of Scientific Articles Using Coherence Patterns
TLDR
This work introduces a graph-based approach to summarize scientific articles using coherence patterns in a corpus of abstracts and proposes a method to combine coherence, importance and non-redundancy to generate the summary. Expand
Ranking Sentences for Extractive Summarization with Reinforcement Learning
TLDR
This paper conceptualize extractive summarization as a sentence ranking task and proposes a novel training algorithm which globally optimizes the ROUGE evaluation metric through a reinforcement learning objective. Expand
Towards Abstractive Multi-Document Summarization Using Submodular Function-Based Framework, Sentence Compression and Merging
We propose a submodular function-based summarization system which integrates three important measures namely importance, coverage, and non-redundancy to detect the important sentences for theExpand
Robust Single-Document Summarizations and a Semantic Measurement of Quality
TLDR
This paper uses the softplus function to enhance keyword rankings to favor important sentences, based on which a number of extractive summarization algorithms are presented using various keyword extraction and topic clustering methods to generate an effective summary for a given document with specific realtime requirements. Expand
Extractive Summarization: Limits, Compression, Generalized Model and Heuristics
TLDR
The concept of compressibility of a document is defined and a new model of summarization is presented, which generalizes existing models in the literature and integrates several dimensions of the summarization, viz., abstractive versus extractive, single versus multi-document, and syntactic versus semantic. Expand
Towards coherent single-document summarization: an integer linear programming-based approach
TLDR
This paper presents an unsupervised summarization system that relies on Integer Linear Programming as an optimization technique for selecting the smallest subset of sentences of a document maximizing the coverage of relevant concepts and enabling local coherence scoring among the sentences in the generated summaries. Expand
Topic modeling combined with classification technique for extractive multi-document text summarization
  • R. Roul
  • Computer Science
  • Soft Comput.
  • 2021
TLDR
The paper proposes a novel methodology for summarizing a corpus of documents to generate a coherent summary using topic modeling and classification technique and the outcomes show that the proposed model is more promising compared to the well-known text summarization models. Expand
A Hierarchy Transformer Network for Extractive Summaries
TLDR
A Hierarchy Transformer Network based sequence model is proposed to solve the problems of inefficient and inaccurate when summarizing electrical documents and has the two significant advantages of being very interpretable and trained on generated reference summaries by human. Expand
HipoRank: Incorporating Hierarchical and Positional Information into Graph-based Unsupervised Long Document Extractive Summarization
TLDR
This work proposes a novel graph-based ranking model for unsupervised extractive summarization of long documents that leverages positional and hierarchical information grounded in discourse structure to augment a document's graph representation with hierarchy and directionality. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 21 REFERENCES
Integrating Importance, Non-Redundancy and Coherence in Graph-Based Extractive Summarization
TLDR
This work proposes a graph-based method for extractive single-document summarization which considers importance, non-redundancy and local coherence simultaneously, and achieves state-of-the-art results on DUC 2002 data. Expand
Movie Script Summarization as Graph-based Scene Extraction
TLDR
A graph-based model is developed that selects a chain by jointly optimizing its logical progression, diversity, and importance, and produces summaries which are more informative compared to competitive baselines. Expand
The use of MMR, diversity-based reranking for reordering documents and producing summaries
TLDR
This paper presents a method for combining query-relevance with information-novelty in the context of text retrieval and summarization, and preliminary results indicate some benefits for MMR diversity ranking in document retrieval and in single document summarization. Expand
The Use of MMR, Diversity-Based Reranking for Reordering Documents and Producing Summaries
TLDR
A method for combining query-relevance with information-novelty in the context of text retrieval and summarization and preliminary results indicate some benefits for MMR diversity ranking in document retrieval and in single document summarization. Expand
LexRank: Graph-based Lexical Centrality as Salience in Text Summarization
TLDR
A new approach, LexRank, for computing sentence importance based on the concept of eigenvector centrality in a graph representation of sentences is considered and the LexRank with threshold method outperforms the other degree-based techniques including continuous LexRank. Expand
Exploiting neighborhood knowledge for single document summarization and keyphrase extraction
TLDR
This article proposes using a small number of nearest neighbor documents to improve document summarization and keyphrase extraction for the specified document, under the assumption that the neighbor documents could provide additional knowledge and more clues. Expand
ROUGE: A Package for Automatic Evaluation of Summaries
TLDR
Four different RouGE measures are introduced: ROUGE-N, ROUge-L, R OUGE-W, and ROUAGE-S included in the Rouge summarization evaluation package and their evaluations. Expand
Graph-based Local Coherence Modeling
TLDR
A computationally efficient graph-based approach for local coherence modeling that is comparable to entity grid based approaches though these rely on a computationally expensive training phase and face data sparsity problems. Expand
A Study of Global Inference Algorithms in Multi-document Summarization
TLDR
This work defines a general framework for inference in summarization and presents three algorithms: a greedy approximate method, a dynamic programming approach based on solutions to the knapsack problem, and an exact algorithm that uses an Integer Linear Programming formulation of the problem. Expand
Three Knowledge-Free Methods for Automatic Lexical Chain Extraction
TLDR
This work presents three approaches to lexical chaining based on the LDA topic model and evaluates them intrinsically on a manually annotated set of German documents, showing that the three methods yield a different chaining behavior, which could be utilized in tasks that use lexicalChaining as a component within NLP applications. Expand
...
1
2
3
...