Data Augmentation Techniques for Process Extraction from Scientific Publications
Fuente:
arXiv
Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915242225696768 |
|---|---|
| author | Susanti, Yuni |
| author_facet | Susanti, Yuni |
| contents | We present data augmentation techniques for process extraction tasks in scientific publications. We cast the process extraction task as a sequence labeling task where we identify all the entities in a sentence and label them according to their process-specific roles. The proposed method attempts to create meaningful augmented sentences by utilizing (1) process-specific information from the original sentence, (2) role label similarity, and (3) sentence similarity. We demonstrate that the proposed methods substantially improve the performance of the process extraction model trained on chemistry domain datasets, up to 12.3 points improvement in performance accuracy (F-score). The proposed methods could potentially reduce overfitting as well, especially when training on small datasets or in a low-resource setting such as in chemistry and other scientific domains. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_14594 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Data Augmentation Techniques for Process Extraction from Scientific Publications Susanti, Yuni Computation and Language Information Retrieval We present data augmentation techniques for process extraction tasks in scientific publications. We cast the process extraction task as a sequence labeling task where we identify all the entities in a sentence and label them according to their process-specific roles. The proposed method attempts to create meaningful augmented sentences by utilizing (1) process-specific information from the original sentence, (2) role label similarity, and (3) sentence similarity. We demonstrate that the proposed methods substantially improve the performance of the process extraction model trained on chemistry domain datasets, up to 12.3 points improvement in performance accuracy (F-score). The proposed methods could potentially reduce overfitting as well, especially when training on small datasets or in a low-resource setting such as in chemistry and other scientific domains. |
| title | Data Augmentation Techniques for Process Extraction from Scientific Publications |
| topic | Computation and Language Information Retrieval |
| url | https://arxiv.org/abs/2405.14594 |