Authors: Alexander M. Rush , Sumit Chopra , Jason Weston - Conference on Empirical Methods in Natural Language Processing, EMNLP 2015 cited by 705
Summarization based on text extraction is inherently limited, but generation-style abstractive methods have proven challenging to build. In this work, we propose a fully data-driven approach to abstractive sentence summarization. Our method utilizes a local attention-based model that generates each word of the summary conditioned on the input sentence. While the model is structurally simple, it can easily be trained end-to-end and scales to a large amount of training data. The model shows significant performance gains on the DUC-2004 shared task compared with several strong baselines.
✨ Checking sign-in… PDF Cited by View BibTeX Hide BibTeX View BibTeX Cite
Headline Generation Based on Statistical… Headline Generation Based on Statistical Translation Hedge Trimmer Hedge Trimmer Minimum Error Rate Training in Statistical… Minimum Error Rate Training in Statistical Machine Translation ROUGE: A Package for Automatic Evaluation of… ROUGE: A Package for Automatic Evaluation of Summaries Hierarchical Probabilistic Neural… Hierarchical Probabilistic Neural Network Language Model Moses: Open Source Toolkit for Statistical… Moses: Open Source Toolkit for Statistical Machine Translation DUC in context DUC in context Sentence Compression Beyond Word Deletion Sentence Compression Beyond Word Deletion Annotated Gigaword Annotated Gigaword Improving neural networks by preventing… Improving neural networks by preventing co-adaptation of feature detectors Overcoming the Lack of Parallel Data in… Overcoming the Lack of Parallel Data in Sentence Compression The Stanford CoreNLP Natural Language… The Stanford CoreNLP Natural Language Processing Toolkit openalex_id:w2962972512 openalex_id:w2962972512 Exploring the Limits of Language Modeling Exploring the Limits of Language Modeling Distraction-based neural networks for modeling… Distraction-based neural networks for modeling documents Long Short-Term Memory-Networks for… Long Short-Term Memory-Networks for Machine Reading From Softmax to Sparsemax: A Sparse… From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label Classification Enhancing and Combining Sequential and Tree LST… Enhancing and Combining Sequential and Tree LSTM for Natural Language Inference Don't Give Me the Details, Just the… Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization Hierarchical Neural Story Generation Hierarchical Neural Story Generation A Discourse-Aware Attention Model for… A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents A Hierarchical Structured… A Hierarchical Structured Self-Attentive Model for Extractive Document Summarization (HSSAS) Improving Abstraction in Text Summarization Improving Abstraction in Text Summarization A Framework for Word Embedding Based… A Framework for Word Embedding Based Automatic Text Summarization and Evaluation A Neural Attention Model for Abstractive Sentenc… A Neural Attention Model for Abstractive Sentence Summarization Earlier references Focus paper Citing papers Older Newer Click a node to pin it, click the empty canvas to go back to this paper, or hover to preview. Open a node’s page from its title.
