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

Showing 110 of 149 papers

TitleStatusHype
Syntactically Look-Ahead Attention Network for Sentence CompressionCode1
Non-Autoregressive Text Generation with Pre-trained Language ModelsCode1
Unsupervised Abstractive Dialogue Summarization with Word Graphs and POV ConversionCode1
Efficient Unsupervised Sentence Compression by Fine-tuning Transformers with Reinforcement LearningCode1
Globally Normalized Transition-Based Neural NetworksCode0
Improving Factual Consistency in Summarization with Compression-Based Post-EditingCode0
Keyphrase Extraction for N-best Reranking in Multi-Sentence CompressionCode0
Evaluation Discrepancy Discovery: A Sentence Compression Case-studyCode0
A Novel Metric for Evaluating Semantics PreservationCode0
Contextualized Semantic Distance between Highly Overlapped TextsCode0
Show:102550
← PrevPage 1 of 15Next →

Benchmark Results

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