Automated Resolution of Noisy Bibliographic References

TL;DR

This paper presents a new method for accurately resolving noisy bibliographic references from OCR scans by integrating correction, parsing, and matching processes inspired by dependency grammars, improving recall over traditional approaches.

Contribution

It introduces a novel approach that merges correction, parsing, and matching steps for noisy references, enhancing accuracy in bibliographic data retrieval.

Findings

The proposed method improves recall in resolving noisy references.

Heuristics significantly enhance the system's effectiveness.

The approach outperforms traditional sequential correction and matching methods.

Abstract

We describe a system used by the NASA Astrophysics Data System to identify bibliographic references obtained from scanned article pages by OCR methods with records in a bibliographic database. We analyze the process generating the noisy references and conclude that the three-step procedure of correcting the OCR results, parsing the corrected string and matching it against the database provides unsatisfactory results. Instead, we propose a method that allows a controlled merging of correction, parsing and matching, inspired by dependency grammars. We also report on the effectiveness of various heuristics that we have employed to improve recall.