Papers › Don't Eclipse Your Arts Due to Small Discrepancies: Boundary Repositioning with a...

Don't Eclipse Your Arts Due to Small Discrepancies: Boundary Repositioning with a Pointer Network for Aspect Extraction

1 Jul 2020ACL 2020 6archive 2025-07-28

Zhenkai Wei, Yu Hong, Bowei Zou, Meng Cheng, Jianmin Yao

The current aspect extraction methods suffer from boundary errors. In general, these errors lead to a relatively minor difference between the extracted aspects and the ground-truth. However, they hurt the performance severely. In this paper, we propose to utilize a pointer network for repositioning the boundaries. Recycling mechanism is used, which enables the training data to be collected without manual intervention. We conduct the experiments on the benchmark datasets SE14 of laptop and SE14-16 of restaurant. Experimental results show that our method achieves substantial improvements over the baseline, and outperforms state-of-the-art methods.

PaperPDF

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

Aspect Extraction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Aspect Extraction SemEval 2015 Task 12 Wei et al. (2020) Restaurant (F1) 72.7 #2 of 2 Archive leaderboard report
Aspect Extraction SemEval-2014 Task-4 Wei et al. (2020) Laptop (F1) 82.7 #5 of 6 Archive leaderboard report
Aspect Extraction SemEval-2014 Task-4 Wei et al. (2020) Restaurant (F1) 87.1 #5 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.

Methods

LSTMPointer NetworkSigmoid ActivationSoftmaxTanh Activation

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