Corpus ID: 7290594

Enhancing Single-Document Summarization by Combining RankNet and Third-Party Sources

@inproceedings{Svore2007EnhancingSS,
  title={Enhancing Single-Document Summarization by Combining RankNet and Third-Party Sources},
  author={K. Svore and Lucy Vanderwende and C. Burges},
  booktitle={EMNLP},
  year={2007}
}
We present a new approach to automatic summarization based on neural nets, called NetSum. We extract a set of features from each sentence that helps identify its importance in the document. We apply novel features based on news search query logs and Wikipedia entities. Using the RankNet learning algorithm, we train a pair-based sentence ranker to score every sentence in the document and identify the most important sentences. We apply our system to documents gathered from CNN.com, where each… Expand
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
Neural Summarization by Extracting Sentences and Words
TLDR
This work develops a general framework for single-document summarization composed of a hierarchical document encoder and an attention-based extractor that allows for different classes of summarization models which can extract sentences or words. Expand
Neural Extractive Summarization with Side Information
TLDR
It is shown that extractive summarization with side information consistently outperforms its counterpart that does not use any side information, in terms of both informativeness and fluency. 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
Document summarization based on semantic representations
TLDR
A novel extractive summarization method based on semantic vector representation that outperforms comparison methods and uses greedy search algorithm to extract the summary sentences. 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
A Supervised Aggregation Framework for Multi-Document Summarization
TLDR
A novel supervised aggregation approach for summarization is proposed which combines different summarization methods including LexPageRank, LexHITS, manifold-ranking method and DivRank and the results demonstrate the effectiveness of the supervised aggregation method compared with typical ensemble approaches. 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
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
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
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 49 REFERENCES
Multi-Document Summarization by Maximizing Informative Content-Words
We show that a simple procedure based on maximizing the number of informative content-words can produce some of the best reported results for multi-document summarization. We first assign a score toExpand
The PYTHY Summarization System: Microsoft Research at DUC 2007
PYTHY is a trainable extractive summarization engine that learns a log-linear sentence ranking model by maximizing three metrics of sentence goodness: two of the metrics are based on ROUGE scoresExpand
A compositional context sensitive multi-document summarizer: exploring the factors that influence summarization
TLDR
The research shows that a frequency based summarizer can achieve performance comparable to that of state-of-the-art systems, but only with a good composition function; context sensitivity improves performance and significantly reduces repetition. Expand
Microsoft Research at DUC2006: Task-Focused Summarization with Sentence Simplification and Lexical Expansion
TLDR
The authors' DUC2006 system comprised three main components: a task-focused extractive summarization system, sentence simplification, and lexical expansion of topic words, which ranked first in terms of both overall mean score and averaged per-cluster mean ranking in the Pyramid evaluation. Expand
NTT's Text Summarization System for DUC-2002
TLDR
The result of the Single-Document Summarization task shows that the summarization system employs the machine learning algorithm, Support Vector Machines, to classify a sentence into an important or an unimportant sentence. Expand
Description of the UAM system for generating very short summaries at DUC-2004 ∗
This paper describes the techniques used for producing very short summaries (around 75 bytes) of single documents. As in last year’s version, the processing has been divided into two separate steps:Expand
Trainable, Scalable Summarization Using Robust NLP and Machine Learning
TLDR
A trainable and scalable summarization system which utilizes features derived from information retrieval, information extraction, and NLP techniques and on-line resources and is demonstrated system scalability by reporting results on the best combination of summarization features for different document sources. Expand
Query Independent Sentence Scoring approach to DUC 2006
TLDR
The task in Document Understanding Conferences (DUC 1 ) 2006 is to generate a fixed length, user oriented, multi document summary, which remains same as that of DUC 2005, and the use of web in scoring the sentences in a query independent manner. 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
Using Hidden Markov Modeling to Decompose Human-Written Summaries
TLDR
A hidden Markov model solution to the decomposition problem of summary sentence decomposition is proposed, which can lead to better text generation techniques for summarization. Expand
...
1
2
3
4
5
...