What Is Collaborative Filtering?
Collaborative filtering recommends items from patterns of interactions among many users and items rather than analyzing item content alone.
Don't Just Read it – Explore It
Collaborative filtering recommends items from patterns of interactions among many users and items rather than analyzing item content alone.
Neural information retrieval uses learned representations and ranking models to find documents or passages relevant to a query.
Learning to rank trains a model to order search results, recommendations, or other candidates according to their predicted usefulness.
Automatic text summarization produces a shorter version of a document or collection while trying to preserve the most important information.
Semantic parsing converts a natural-language request into a structured representation that a computer can execute or reason over.
Coreference resolution determines which words or phrases in a passage refer to the same person, object, event, or idea.
Topic modeling discovers recurring word patterns in a document collection and represents documents as mixtures of latent themes.
Named entity recognition finds spans of text that refer to entities such as people, organizations, places, dates, or products.
Sentiment analysis estimates opinions or attitudes expressed in text, often as positive, negative, neutral, or more detailed categories.
Neural machine translation uses a trained neural model to convert a sequence in one language into a sequence in another.
Speaker diarization divides a recording into segments according to who spoke when, without necessarily knowing each person’s identity.
Voice activity detection estimates which moments in an audio stream contain speech and which contain silence or other sounds.