Optimized Table Tokenization for Table Structure Recognition
This work addresses the need for efficient and accurate table extraction in document conversion pipelines, representing an incremental improvement over existing transformer-based methods.
The paper tackled the problem of table structure recognition by proposing an optimized table-structure language (OTSL) that reduces token count to 5 (compared to 28+ in HTML) and halves sequence length, resulting in significantly improved model accuracy, halved inference time, and syntactically correct predictions that eliminate most post-processing needs.
Extracting tables from documents is a crucial task in any document conversion pipeline. Recently, transformer-based models have demonstrated that table-structure can be recognized with impressive accuracy using Image-to-Markup-Sequence (Im2Seq) approaches. Taking only the image of a table, such models predict a sequence of tokens (e.g. in HTML, LaTeX) which represent the structure of the table. Since the token representation of the table structure has a significant impact on the accuracy and run-time performance of any Im2Seq model, we investigate in this paper how table-structure representation can be optimised. We propose a new, optimised table-structure language (OTSL) with a minimized vocabulary and specific rules. The benefits of OTSL are that it reduces the number of tokens to 5 (HTML needs 28+) and shortens the sequence length to half of HTML on average. Consequently, model accuracy improves significantly, inference time is halved compared to HTML-based models, and the predicted table structures are always syntactically correct. This in turn eliminates most post-processing needs.