Papers › An Information Extraction Study: Take In Mind the Tokenization!

An Information Extraction Study: Take In Mind the Tokenization!

27 Mar 2023arXiv:2303.15100archive 2025-07-28

Christos Theodoropoulos, Marie-Francine Moens

Current research on the advantages and trade-offs of using characters, instead of tokenized text, as input for deep learning models, has evolved substantially. New token-free models remove the traditional tokenization step; however, their efficiency remains unclear. Moreover, the effect of tokenization is relatively unexplored in sequence tagging tasks. To this end, we investigate the impact of tokenization when extracting information from documents and present a comparative study and analysis of subword-based and character-based models. Specifically, we study Information Extraction (IE) from biomedical texts. The main outcome is twofold: tokenization patterns can introduce inductive bias that results in state-of-the-art performance, and the character-based models produce promising results; thus, transitioning to token-free IE models is feasible.

PaperPDFCode

Code

christos42/inductive_bias_IE officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Inductive BiasNamed Entity Recognition (NER)Relation Extraction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Relation Extraction Adverse Drug Events (ADE) Corpus PFN (ALBERT XXL, average aggregation) NER Macro F1 91.5 #2 of 15 Archive leaderboard report
Relation Extraction Adverse Drug Events (ADE) Corpus PFN (ALBERT XXL, average aggregation) RE+ Macro F1 83.9 #2 of 15 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections