Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2405.02525 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916279223320576 |
|---|---|
| author | Bin-Hezam, Reem Stevenson, Mark |
| author_facet | Bin-Hezam, Reem Stevenson, Mark |
| contents | We present RLStop, a novel Technology Assisted Review (TAR) stopping rule based on reinforcement learning that helps minimise the number of documents that need to be manually reviewed within TAR applications. RLStop is trained on example rankings using a reward function to identify the optimal point to stop examining documents. Experiments at a range of target recall levels on multiple benchmark datasets (CLEF e-Health, TREC Total Recall, and Reuters RCV1) demonstrated that RLStop substantially reduces the workload required to screen a document collection for relevance. RLStop outperforms a wide range of alternative approaches, achieving performance close to the maximum possible for the task under some circumstances. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_02525 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | RLStop: A Reinforcement Learning Stopping Method for TAR Bin-Hezam, Reem Stevenson, Mark Information Retrieval We present RLStop, a novel Technology Assisted Review (TAR) stopping rule based on reinforcement learning that helps minimise the number of documents that need to be manually reviewed within TAR applications. RLStop is trained on example rankings using a reward function to identify the optimal point to stop examining documents. Experiments at a range of target recall levels on multiple benchmark datasets (CLEF e-Health, TREC Total Recall, and Reuters RCV1) demonstrated that RLStop substantially reduces the workload required to screen a document collection for relevance. RLStop outperforms a wide range of alternative approaches, achieving performance close to the maximum possible for the task under some circumstances. |
| title | RLStop: A Reinforcement Learning Stopping Method for TAR |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2405.02525 |