Revealing the structure of medical dictations with conditional random fields

Jeremy Jancsary, Johannes Matiasek, and Harald Trost
2008 Conference on Empirical Methods in Natural Language Processing (EMNLP)
October 2008, Honolulu, Hawaii, USA

Automatic processing of medical dictations poses a significant challenge. We approach the problem by introducing a statistical framework capable of identifying types and bound- aries of sections, lists and other structures occurring in a dictation, thereby gaining explicit knowledge about the function of such elements. Training data is created semi-automatically by aligning a parallel corpus of corrected medical reports and corresponding transcripts generated via automatic speech recognition. We highlight the properties of our statistical framework, which is based on conditional random fields (CRFs) and implemented as an efficient, publicly available toolkit. Finally, we show that our approach is effective both under ideal conditions and for real-life dictation involving speech recognition errors and speech-related phenomena such as hesitation and repetitions.

Article

 

Note: VieCRF, the software package used in the paper, is available on the Software page.

Please cite as:

@INPROCEEDINGS{Jancsary2008b,
title = {Revealing the structure of medical dictations with conditional random fields},
author = {Jeremy Jancsary and Johannes Matiasek and Harald Trost},
booktitle = {2008 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
year = {2008}
}