# Syntactically Look-Ahead Attention Network for Sentence Compression

Source: [Syntactically Look-Ahead Attention Network for Sentence Compression](<https://www.sota2.com/research/paper/68fa67891e209131cea16c56>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T03:11:52.180Z

Authors: Hidetaka Kamigaito, Manabu Okumura

Published: 2020-02-04T06:26:37.000Z

## Abstract

Sentence compression is the task of compressing a long sentence into a short one by deleting redundant words. In sequence-to-sequence (Seq2Seq) based models, the decoder unidirectionally decides to retain or delete words. Thus, it cannot usually explicitly capture the relationships between decoded words and unseen words that will be decoded in the future time steps. Therefore, to avoid generating ungrammatical sentences, the decoder sometimes drops important words in compressing sentences. To solve this problem, we propose a novel Seq2Seq model, syntactically look-ahead attention network (SLAHAN), that can generate informative summaries by explicitly tracking both dependency parent and child words during decoding and capturing important words that will be decoded in the future. The results of the automatic evaluation on the Google sentence compression dataset showed that SLAHAN achieved the best kept-token-based-F1, ROUGE-1, ROUGE-2 and ROUGE-L scores of 85.5, 79.3, 71.3 and 79.1, respectively. SLAHAN also improved the summarization performance on longer sentences. Furthermore, in the human evaluation, SLAHAN improved informativeness without losing readability.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Sentence Compression on Google dataset ALL (test)](<https://www.sota2.com/research/sota/sentence-compression-on-google-dataset-all-test.md>): Sentence Compression; Google dataset ALL (test); F1 Score: 85.5.

- [Sentence Compression on BNC Corpus (out-of-domain)](<https://www.sota2.com/research/sota/sentence-compression-on-bnc-corpus-out-of-domain.md>): Sentence Compression; BNC Corpus (out-of-domain); F1 Score: 0.577.

- [Sentence Compression on Google dataset LONG (test)](<https://www.sota2.com/research/sota/sentence-compression-on-google-dataset-long-test.md>): Sentence Compression; Google dataset LONG (test); F1 Score: 0.836.

- [Sentence Compression on Google (test)](<https://www.sota2.com/research/sota/sentence-compression-on-google-test.md>): Sentence Compression; Google (test); Read Score: 3.91.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2002.01145>)

[PDF](<https://arxiv.org/pdf/2002.01145.pdf>)

[Implementation](<https://github.com/kamigaito/slahan.>)