Papers › A Language Model based Evaluator for Sentence Compression

A Language Model based Evaluator for Sentence Compression

1 Jul 2018ACL 2018 7archive 2025-07-28

Yang Zhao, Zhiyuan Luo, Akiko Aizawa

We herein present a language-model-based evaluator for deletion-based sentence compression and view this task as a series of deletion-and-evaluation operations using the evaluator. More specifically, the evaluator is a syntactic neural language model that is first built by learning the syntactic and structural collocation among words. Subsequently, a series of trial-and-error deletion operations are conducted on the source sentences via a reinforcement learning framework to obtain the best target compression. An empirical study shows that the proposed model can effectively generate more readable compression, comparable or superior to several strong baselines. Furthermore, we introduce a 200-sentence test set for a large-scale dataset, setting a new baseline for the future research.

Paper PDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Language Modeling Language Modelling Reinforcement Learning Reinforcement Learning (RL)Sentence Sentence Compression model reinforcement-learning

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Sentence Compression	Google Dataset	BiRNN + LM Evaluator	CR	0.39	#2 of 6	Archive leaderboard	report
Sentence Compression	Google Dataset	BiRNN + LM Evaluator	F1	0.851	#2 of 6	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections