LAME: Layout-Aware Metadata Extraction Approach for Research Articles
Source abstract
Abstract
The volume of academic literature, such as academic conference papers and journals, has increased rapidly worldwide, and research on metadata extraction is ongoing. However, high-performing metadata extraction is still challenging due to diverse layout formats according to journal publishers. To accommodate the diversity of the layouts of academic journals, we propose a novel LAyout-aware Metadata Extraction (LAME) framework equipped with the three characteristics (e.g., design of automatic layout analysis, construction of a large meta-data training set, and implementation of metadata extractor). In the framework, we designed an automatic layout analysis using PDFMiner. Based on the layout analysis, a large volume of metadata-separated training data, including the title, abstract, author name, author affiliated organization, and keywords, were automatically extracted. Moreover, we constructed a pre-trained model, Layout-MetaBERT, to extract the metadata from academic journals with varying layout formats. The experimental results with our metadata extractor exhibited robust performance (Macro-F1, 93.27%) in metadata extraction for unseen journals with different layout formats.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Handwritten Text Recognition Techniques · Web Data Mining and Analysis · Image Retrieval and Classification Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (27)
Show source-provided references
1. Publaynet: Largest dataset ever for document layout analysis
2. Document layout analysis using multigaussian fitting
3. DocBank: A benchmark dataset for document layout analysis
4. CERMINE: Automatic extraction of structured metadata from scientific literature
5. GROBID: Combining automatic bibliographic data recognition and term extraction for scholarship publications
6. Metadata extraction based on deep learning from academic paper in pdf10.5626/JOK.2019.46.7.644 ↗
7. Layoutlm: Pre-training of text and layout for document image understanding
8. Mask r-cnn
9. Fast r-cnn
10. BERT: Pre-training of deep bidirectional transformers for language understanding
11. Automatic document metadata extraction using support vector machines
12. Sequence classification with neural conditional random fields
13. Y. Kim, “Convolutional neural networks for sentence classification,” MS thesis, University of Waterloo, 2015.10.3115/v1/D14-1181 ↗
14. Text classification improved by integrating bidirectional LSTM with two-dimensional max pooling
15. A. Adhikari, A. Ram, R. Tang and J. Lin, “DocBERT: BERT for document classification,” arXiv preprint arXiv:1904.08398, 2019. [Online]. Available: http://arxiv.org/abs/1904.08398.
16. Improving bert-based text classification with auxiliary sentence and domain knowledge10.1109/ACCESS.2019.2953990 ↗
17. X. Gu, K. M. Yoo and J. Ha, “DialogBERT: Discourse-aware response generation via learning to recover and rank utterances,” arXiv preprint arXiv:2012.01775v1, 2021. [Online]. Available: https://arxiv.org/abs/2012.01775.
18. ALBERT: A lite BERT for self-supervised learning of language representations
19. SciBERT: A pretrained language model for scientific text
20. Chargrid: Towards understanding 2d documents
21. Ł Garncarek, R. Powalski and T. Stanisławek, “LAMBERT: Layout-aware (language) modeling for information extraction,” in arXiv preprint arXiv:2002.08087, 2020. [Online]. Available: https://arxiv.org/abs/2002.08087.
22. Object detection with deep learning: A review10.1109/TNNLS.2018.2876865 ↗
23. Tightness-aware evaluation protocol for scene text detection
24. A fast algorithm for bottom-up document layout analysis10.1109/34.584106 ↗
25. Bleu: A method for automatic evaluation of machine translation
26. BioBERT: A pre-trained biomedical language representation model for biomedical text mining10.1093/bioinformatics/btz682 ↗
27. Y. Wu, M. Schuster, Z. Chen, Q. Le, M. Norouzi et al., “Google's neural machine translation system: Bridging the gap between human and machine translation,” arXiv preprint arXiv:1609.08144, 2016. [Online]. Available: https://arxiv.org/abs/1609.08144v2.