A Framework For Refining Text Classification and Object Recognition from Academic Articles
Jinghong Li, Koichi Ota, Wen Gu, Shinobu Hasegawa
TL;DR
The paper tackles automated extraction of structured information from academic PDFs with irregular layouts. It introduces the Text Block Refinement Framework (TBRF), a hybrid system that combines rule-based detection with a lightweight machine-learning module, anchored by an encoder template and small-scale human annotations. The approach demonstrates high performance on ACL proceedings, achieving over $95\%$ accuracy in text-block classification and over $90\%$ accuracy for locating figures and tables, using a compact training set. These results suggest practical gains in reducing annotation effort and improving robustness of document understanding tasks across scholarly articles.
Abstract
With the widespread use of the internet, it has become increasingly crucial to extract specific information from vast amounts of academic articles efficiently. Data mining techniques are generally employed to solve this issue. However, data mining for academic articles is challenging since it requires automatically extracting specific patterns in complex and unstructured layout documents. Current data mining methods for academic articles employ rule-based(RB) or machine learning(ML) approaches. However, using rule-based methods incurs a high coding cost for complex typesetting articles. On the other hand, simply using machine learning methods requires annotation work for complex content types within the paper, which can be costly. Furthermore, only using machine learning can lead to cases where patterns easily recognized by rule-based methods are mistakenly extracted. To overcome these issues, from the perspective of analyzing the standard layout and typesetting used in the specified publication, we emphasize implementing specific methods for specific characteristics in academic articles. We have developed a novel Text Block Refinement Framework (TBRF), a machine learning and rule-based scheme hybrid. We used the well-known ACL proceeding articles as experimental data for the validation experiment. The experiment shows that our approach achieved over 95% classification accuracy and 90% detection accuracy for tables and figures.