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 11–20 of 149 papers

TitleStatusHype
SOM-NCSCM : An Efficient Neural Chinese Sentence Compression Model Enhanced with Self-Organizing Map—0
A Novel Metric for Evaluating Semantics PreservationCode0
Leveraging Information Bottleneck for Scientific Document Summarization—0
Contextualized Semantic Distance between Highly Overlapped TextsCode0
Cross-Register Projection for Headline Part of Speech Tagging—0
RepSum: Unsupervised Dialogue Summarization based on Replacement Strategy—0
Etat de l’art en compression multi-phrases pour la synthèse de documents (State-of-the-art of multi-sentence compression for document summarization)—0
Non-Autoregressive Text Generation with Pre-trained Language ModelsCode1
With Measured Words: Simple Sentence Selection for Black-Box Optimization of Sentence Compression Algorithms—0
Evaluation Discrepancy Discovery: A Sentence Compression Case-studyCode0
Show:102550
← PrevPage 2 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