# Improving sentence compression by learning to predict gaze

Source: [Improving sentence compression by learning to predict gaze](<https://www.sota2.com/research/paper/68fa62681e209131ce9f9365>)

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

Data updated: 2026-01-04T02:42:57.904Z

Authors: Sigrid Klerke, Yoav Goldberg, Anders S{\\o}gaard

Published: 2016-04-12T11:57:05.000Z

## Abstract

We show how eye-tracking corpora can be used to improve sentence compression models, presenting a novel multi-task learning algorithm based on multi-layer LSTMs. We obtain performance competitive with or better than state-of-the-art approaches.

## 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 (test)](<https://www.sota2.com/research/sota/sentence-compression-on-google-test.md>): Sentence Compression; Google (test); Read Score: 3.9.

- [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: 0.83.

- [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: 0.546.

- [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.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1604.03357>)

[PDF](<https://arxiv.org/pdf/1604.03357.pdf>)

[Implementation](<https://bitbucket.org/soegaard/gaze-mtl16>)