Summary of Text-based Detection Of On-hold Scripts in Contact Center Calls, by Dmitrii Galimzianov et al.
Text-Based Detection of On-Hold Scripts in Contact Center Calls
by Dmitrii Galimzianov, Viacheslav Vyshegorodtsev
First submitted to arxiv on: 13 Jul 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary A novel natural language processing (NLP) model is introduced, capable of detecting on-hold phrases in customer service calls transcribed via automatic speech recognition technology. This model tackles the multiclass text classification problem, categorizing dialogue turns into three mutually exclusive classes: on-hold scripts, return-to-client scripts, and irrelevant phrases. By fine-tuning RuBERT on an in-house dataset, high model performance is achieved, potentially aiding agent monitoring by verifying adherence to predefined on-hold scripts. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary A new computer program can help customer service centers track what their agents say to customers when they’re put on hold. The program uses special language processing techniques to identify specific phrases that are meant for holding or returning a call. This can be helpful in making sure agents follow the correct scripts and improve overall customer satisfaction. |
Keywords
* Artificial intelligence * Fine tuning * Natural language processing * Nlp * Text classification
