Enhancing Common Natural Language Processing with Cognitive...
summary
Claims a cognitive layer plus standard NLP improves signal detection by producing a pair of metrics (blue vs red) that map deliberate versus habitual language. Uses sentiment analysis, named entity recognition, topic modeling and a Python package served as Flask APIs. Focuses modeling on low Delta passages (throwing out ~60–70% of text) or one‑third of tweets to reduce noise. Finds a legal-team whistleblower in Enron mail, builds a “made my day” five‑star insecurity filter, and uses the output for e‑discovery and anomaly alerts.
AI-written summary · about
chapters (12)
- 0:00Introduction
- 1:08Cognitive language models
- 4:25Cognitive NLP vs traditional
- 7:17Topic modeling Enron emails
- 11:11Trump tweets 2019 analysis
- 13:31Cognitive model foundation
- 18:00Q&A model robustness
- 28:05Fraud detection emails
- 31:38Legal business use cases
- 35:10Reviews model limits
- 36:30Future plans explainability
- 37:54Closing remarks
related talks
32mHow to be best in conveying the message by using NLP approach (Big Five modeling)
12mRevolutionizing Cloud-Native Applications with NLP
23mCognitive Architecture for Process industries
47mBeyond the Usual Suspects: Emerging Cognitive Services
34mCan automated responses to cyber incidents be supported by AI?
26mAdding Narrative to BI Dashboards with Natural Language...
15mNatural Language-Guided Programming
40mBeyond the Hype: Realistic Expectations of AI