natural-language-processing-2

Sentence Compression

3260 papers • 126 benchmarks • 313 datasets

Sentence Compression is the task of reducing the length of text by removing non-essential content while preserving important facts and grammaticality.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in sentence-compression-5

Trend

Dataset

Best Model

Actions

Google Dataset

Libraries

i

Use these libraries to find sentence-compression-5 models and implementations

Datasets

Sentence Compression

Google

Subtasks

Unsupervised Sentence Compression

Most implemented papers

Unsupervised Abstractive Meeting Summarization with Multi-Sentence Compression and Budgeted Submodular Maximization

A. Tixier, M. Vazirgiannis, Guokan Shang, Wensi Ding, Zekun Zhang, Polykarpos Meladianos, J. Lorré•Sun May 13 2018

A novel graph-based framework for abstractive meeting speech summarization that is fully unsupervised and does not rely on any annotations to take exterior semantic knowledge into account, and to design custom diversity and informativeness measures.

128

Content

0

Paper Graph

Keyphrase Extraction for N-best Reranking in Multi-Sentence Compression

Florian Boudin, E. Morin•Sun Jun 09 2013

This paper presents an N-best reranking method based on keyphrase extraction that significantly improves the informativity of the generated compressions.

85 0

Paper Graph

Globally Normalized Transition-Based Neural Networks

Chris Alberti, Michael Collins, Slav Petrov, D. Andor, A. Severyn, David Weiss, Alessandro Presta, Kuzman Ganchev•Fri Mar 18 2016

A globally normalized transition-based neural network model that achieves state-of-the-art part- of-speech tagging, dependency parsing and sentence compression results is introduced.

571 0

Paper Graph

Sentence Simplification with Deep Reinforcement Learning

Xingxing Zhang, Mirella Lapata•Thu Mar 30 2017

This work addresses the simplification problem with an encoder-decoder model coupled with a deep reinforcement learning framework, and explores the space of possible simplifications while learning to optimize a reward function that encourages outputs which are simple, fluent, and preserve the meaning of the input.

413 0

Paper Graph

Learning How to Simplify From Explicit Labeling of Complex-Simplified Text Pairs

Carolina Scarton, Lucia Specia, Fernando Alva-Manchego, Gustavo Paetzold, Joachim Bingel•Tue Oct 31 2017

A way to automatically identify operations in a parallel corpus and introduce a sequence-labeling approach based on these annotations is devised, which provides insights on the types of transformations that different approaches can model.

73 0

Paper Graph

Combining Graph Degeneracy and Submodularity for Unsupervised Extractive Summarization

A. Tixier, M. Vazirgiannis, Polykarpos Meladianos•Thu Aug 31 2017

A fully unsupervised, extractive text summarization system that leverages a submodularity framework that allows summaries to be generated in a greedy way while preserving near-optimal performance guarantees is presented.

29 0

Paper Graph

Sequence-to-sequence Models for Cache Transition Systems

Xiaochang Peng, Linfeng Song, D. Gildea, G. Satta•Sat Jun 30 2018

This paper transforms the sequence to graph mapping problem to a word sequence to transition action sequence problem using a special transition system called a cache transition system, and presents a monotonic hard attention model for the transition framework to handle the strictly left-to-right alignment between each transition state and the current buffer input focus.

23 0

Paper Graph

Unsupervised Semantic Abstractive Summarization

Vivek Gupta, H. Karnick, Shibhansh Dohare•Sat Jun 30 2018

This work develops a more comprehensive method to generate the story AMR graph using state-of-the-art co-reference resolution and Meta Nodes and outperforms the state of the art SAS method by 1.7% F1 score in node prediction.

22 0

Paper Graph

Unsupervised Sentence Compression using Denoising Auto-Encoders

Jason Phang, Thibault Févry•Thu Sep 06 2018

Although the models are underperform supervised models based on ROUGE scores, their models are competitive with a supervised baseline based on human evaluation for grammatical correctness and retention of meaning.

73 0

Paper Graph

Sentence Compression for Arbitrary Languages via Multilingual Pivoting

Mirella Lapata, Rico Sennrich, Jonathan Mallinson•Wed Oct 31 2018

The use of bilingual corpora which are abundantly available for training sentence compression models are advocated and a new parallel Multilingual Compression dataset is released which can be used to evaluate compression models across languages and genres.

16 0

Paper Graph

Adding a benchmark result helps the community track progress.