Awesome Single Document Summarization

A curated list of resources for Single Document Summarization. The GitHub repository link is here.

Contributing

Please feel free to email Yi Chern Tan (yichern.tan at yale.edu)

Table of Contents

• Tutorials and Blogs
• Papers
  • Metrics
  • Classical Methods
  • Extractive Methods
  • Abstractive Methods
  • Hybrid and Other Methods
• Other Papers
  • Sentence Compression
  • Code Summarization
• Datasets

Tutorials and Blogs

• Text Summarization with Gensim[link]
• How to Prepare News Articles for Text Summarization[link]
• LEX-Rank and Textrank based document summarization system (Interactive tutorial + Java code)[link]
• Text summarization with TensorFlow[link]
• Text Summarization in Python: Extractive vs. Abstractive techniques revisited[link]
• How to Run Text Summarization with TensorFlow[link]
• Taming Recurrent Neural Networks for Better Summarization[link]

Papers

Metrics

• Automatic Evaluation of Summaries Using N-gram Co-Occurrence Statistics (HLT-NAACL 2003)[paper]
• ROUGE: A Package for Automatic Evaluation of Summaries (ACL 2004)[paper][code]
• METEOR: An Automatic Metric for MT Evaluation with Improved Correlation with Human Judgments (ACL 2005)[paper][code]
• Automated Summarization Evaluation with Basic Elements[paper]
• Automated Pyramid Scoring of Summaries using Distributional Semantics (ACL 2013)[paper][code]
• Better Summarization Evaluation with Word Embeddings for ROUGE (EMNLP 2015)[paper][code]
• A semantically motivated approach to compute ROUGE scores (EMNLP 2018)[paper]
• Summarization Evaluation in the Absence of Human Model Summaries Using the Compositionality of Word Embeddings (COLING 2018)[paper][code]
• A Graph-theoretic Summary Evaluation for ROUGE (ACL 2018)[paper][code]

Classical Methods

• The Use of MMR, Diversity-Based Reranking for Reordering Documents and Producing Summaries (SIGIR 1998)[paper]
• TextRank: Bringing Order into Texts (EMNLP 2004)[paper][code]
• LexRank: Graph-based Lexical Centrality as Salience in Text Summarization (AAAI 2004)[paper][code][code]
• A Study of Global Inference Algorithms in Multi-Document Summarization (ECIR 2007)[paper]
• A Class of Submodular Functions for Document Summarization (ACL 2011)[paper]

Extractive Methods

• Neural Summarization by Extracting Sentences and Words (ACL 2016)[paper][code]
• SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documents (AAAI 2017)[paper][code]
• Neural Document Summarization by Jointly Learning to Score and Select Sentences (ACL 2018)[paper][code]
• Ranking Sentences for Extractive Summarization with Reinforcement Learning (NAACL 2018)[paper][code]
• Learning to Extract Coherent Summary via Deep Reinforcement Learning (AAAI 2018)[paper]
• Extractive Summarization with SWAP-NET: Sentences and Words from Alternating Pointer Networks (ACL 2018)[paper][code]

Abstractive Methods

• Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond (CoNLL 2016)[paper][code]
• Incorporating Copying Mechanism in Sequence-to-Sequence Learning (ACL 2016)[paper][code]
• Get To The Point: Summarization with Pointer-Generator Networks (ACL 2017)[paper][code]
• Bottom-Up Abstractive Summarization (EMNLP 2018)[paper][code]
• Improving Neural Abstractive Document Summarization with Structural Regulation (EMNLP 2018)[paper]
• Deep Communicating Agents for Abstractive Summarization (ACL 2018)[paper]
• On the Abstractiveness of Neural Document Summarization (EMNLP 2018)[paper]
• Improving Abstraction in Text Summarization (EMNLP 2018)[paper]
• Generative Adversarial Network for Abstractive Text Summarization (AAAI 2018)[paper][code]
• A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents (NAACL 2018)[paper][code]

Hybrid and Other Methods

• Guiding Generation for Abstractive Text Summarization based on Key Information Guide Network (NAACL 2018)[paper]
• Abstractive Document Summarization with a Graph-Based Attentional Neural Model (ACL 2018)[paper][code]
• Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting (ACL 2018)[paper][code]
• Structured Neural Summarization (pending review)[paper]

Other Papers

Sentence Compression

• A Neural Attention Model for Sentence Summarization (ACL 2015)[paper][code]
• Sentence Compression by Deletion with LSTMs (ACL 2015)[paper]
• Abstractive Sentence Summarization with Attentive Recurrent Neural Networks (ACL 2016)[paper]
• Can Syntax Help? Improving an LSTM-based Sentence Compression Model for New Domains (ACL 2017)[paper]
• A Language Model based Evaluator for Sentence Compression (ACL 2018)[paper][code]

Code Summarization

• Learning to Represent Programs with Graphs (ICLR 2018)[paper]
• code2seq: Generating Sequences from Structured Representations of Code (pending review)[paper]
• Structured Neural Summarization (pending review)[paper]

Datasets

• Spreadsheet of Summarization Corpora[link]
• DUC[data]
• TAC[data]
• Gigaword[data]
• Scientific Summarization[data]
• Live Blogs[data]
• Legal Cases[data]
• BBC News Summary[data]
• Opinosis[data]
• Wikihow[data]
• Sentence Compression[data]
• Method2Name[code]
• Method2Doc[code]