Sentence Compression
22 papers with code • 1 benchmarks • 2 datasets
Sentence Compression is the task of reducing the length of text by removing non-essential content while preserving important facts and grammaticality.
Benchmarks
These leaderboards are used to track progress in Sentence Compression
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
Sentence Compression
Google
Most implemented papers
SEQ^3: Differentiable Sequence-to-Sequence-to-Sequence Autoencoder for Unsupervised Abstractive Sentence Compression
cbaziotis/seq3
•
•
The proposed model does not require parallel text-summary pairs, achieving promising results in unsupervised sentence compression on benchmark datasets.
SEQ\^3: Differentiable Sequence-to-Sequence-to-Sequence Autoencoder for Unsupervised Abstractive Sentence Compression
The proposed model does not require parallel text-summary pairs, achieving promising results in unsupervised sentence compression on benchmark datasets.
Explicit Sentence Compression for Neural Machine Translation
bcmi220/esc4nmt
•
•
In this paper, we propose an explicit sentence compression method to enhance the source sentence representation for NMT.
Syntactically Look-Ahead Attention Network for Sentence Compression
kamigaito/SLAHAN
•
•
Sentence compression is the task of compressing a long sentence into a short one by deleting redundant words.
SCAR: Sentence Compression using Autoencoders for Reconstruction
The compressor masks the input, and the reconstructor tries to regenerate it.
Evaluation Discrepancy Discovery: A Sentence Compression Case-study
UKPLab/arxiv2021-evaluation-discrepancy-nsc
•
•
Reliable evaluation protocols are of utmost importance for reproducible NLP research.
Non-Autoregressive Text Generation with Pre-trained Language Models
yxuansu/NAG-BERT
•
•
EACL 2021
In this work, we show that BERT can be employed as the backbone of a NAG model to greatly improve performance.
Contextualized Semantic Distance between Highly Overlapped Texts
Stareru/NeighboringDistributionDivergence
•
•
Overlapping frequently occurs in paired texts in natural language processing tasks like text editing and semantic similarity evaluation.
A Novel Metric for Evaluating Semantics Preservation
Stareru/NeighboringDistributionDivergence
•
•
ACL ARR October 2021
By exploiting the property of NDD, we implement a unsupervised and even training-free algorithm for extractive sentence compression.
Efficient Unsupervised Sentence Compression by Fine-tuning Transformers with Reinforcement Learning
complementizer/rl-sentence-compression
•
•
ACL 2022
Sentence compression reduces the length of text by removing non-essential content while preserving important facts and grammaticality.
