100When would you use a CRF instead of an HMM for sequence labeling, and why?▼hardGoogleMicrosoftAmazon2 replies◆ premiumBoth label sequences, but one is generative and one is discriminative, and that gap decides whether you can add overlapping features. Here is the comparison that proves you understand the modeling tradeoff, not merely the acronyms.Open full answer →
43Design a query understanding system for search.▼hardGoogleAmazonMicrosoft1 replies◆ premiumQuery understanding is the front end of search that converts a raw query into structured intent. Get it wrong and even a perfect index returns garbage. The signal is the pipeline and how you measure it. Here is the design.Open full answer →
18How do you detect and redact PII in text at scale (for LLM inputs, logs, and training data)?▼mediumMicrosoftGoogleAmazon2 replies○ sign inBecause detection never catches everything, the strong answer works in layers: checksummed regex for structured PII, ML/NER for the unstructured PII regex misses, and an honest explanation of why redaction alone is never enough. Here is the answer.Open full answer →
