May I Ask Who's Calling? Named Entity Recognition on Call Center Transcripts for Privacy Law Compliance
This work addresses privacy compliance for call centers by applying NER to a new data type, but it is incremental as it uses existing methods on new data.
The paper tackled Named Entity Recognition on call center transcripts to address privacy law compliance, achieving state-of-the-art results on this novel task.
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.