Discover published sets by community

Based on traditional statistics; used for probability distribution over sequences of words; applications include speech recognition, machine translation, part-of-speech tagging.

Predict the next word in a sequence; use fixed-length previous word sequences; applications in text prediction, auto-complete features, language identification.

Represent probabilistic relationships using a graph; captures dependencies between random variables; applications in semantic role labeling, coreference resolution, and syntactic parsing.

Leverage neural networks; capture continuous word representations; applications include text generation, language translation, sentiment analysis.

Simplified variant of LSTMs; uses update and reset gates; applications include language translation, text summarization, and dialogue generation.

Based on attention mechanisms; parallelizable; applications include state-of-the-art natural language understanding and generation tasks.

Designed to handle sequential data; memory of past computations influences current ones; applications include text generation, speech recognition, and time-series prediction.

Built on pretrained models; fine-tuned for specific tasks; applications include text classification, named entity recognition, question answering.

Utilizes convolutional layers; good for capturing local dependencies; applications include sentence classification, topic categorization, and information extraction.