SOTAVerified

Sentence Compression

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

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–10 of 149 papers

TitleStatusHype
Non-Autoregressive Text Generation with Pre-trained Language ModelsCode1
Efficient Unsupervised Sentence Compression by Fine-tuning Transformers with Reinforcement LearningCode1
Syntactically Look-Ahead Attention Network for Sentence CompressionCode1
Unsupervised Abstractive Dialogue Summarization with Word Graphs and POV ConversionCode1
A Difference-of-Convex Programming Approach With Parallel Branch-and-Bound For Sentence Compression Via A Hybrid Extractive Model—0
Adversarial Neural Networks for Cross-lingual Sequence Tagging—0
Abstractive Unsupervised Multi-Document Summarization using Paraphrastic Sentence Fusion—0
A Multilingual Study of Multi-Sentence Compression using Word Vertex-Labeled Graphs and Integer Linear Programming—0
A Dataset and Evaluation Metrics for Abstractive Compression of Sentences and Short Paragraphs—0
A Language Model based Evaluator for Sentence Compression—0
Show:102550
← PrevPage 1 of 15Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1SLAHAN (LSTM+syntactic-information)F10.86—Unverified
2BiRNN + LM EvaluatorF10.85—Unverified
3Higher-Order Syntactic Attention NetworkF10.84—Unverified
4LSTMF10.82—Unverified
5LSTMs + eye-movementF10.81—Unverified
6BiLSTMF10.8—Unverified