We investigate using Named Entity Recognition on a new type of user-generated text: a call center conversation. These conversations combine problems from spontaneous speech with problems novel to conversational Automated Speech Recognition, including incorrect recognition, alongside other common problems from noisy user-generated text. Using our own corpus with new annotations, training custom contextual string embeddings, and applying a BiLSTM-CRF, we match state-of-the-art results on our novel task.
@article{arxiv.2010.15598,
title = {May I Ask Who's Calling? Named Entity Recognition on Call Center Transcripts for Privacy Law Compliance},
author = {Micaela Kaplan},
journal= {arXiv preprint arXiv:2010.15598},
year = {2020}
}
Comments
The 6th Workshop on Noisy User-generated Text (W-NUT) 2020 at EMNLP