Named Entity Recognition for Address Extraction in Speech-to-Text Transcriptions Using Synthetic Data
This addresses the challenge of limited real data for NER in speech-to-text transcriptions, particularly for Slovak language, but is incremental as it applies existing methods to a new domain with synthetic data.
The paper tackles the problem of extracting address parts from speech-to-text transcriptions by developing a Named Entity Recognition model based on SlovakBERT, using synthetic data generated via GPT API due to data scarcity, and achieves performance evaluated on a small real test dataset.
This paper introduces an approach for building a Named Entity Recognition (NER) model built upon a Bidirectional Encoder Representations from Transformers (BERT) architecture, specifically utilizing the SlovakBERT model. This NER model extracts address parts from data acquired from speech-to-text transcriptions. Due to scarcity of real data, a synthetic dataset using GPT API was generated. The importance of mimicking spoken language variability in this artificial data is emphasized. The performance of our NER model, trained solely on synthetic data, is evaluated using small real test dataset.