N-gram
An N-gram is a contiguous sequence of N items from a text, used in language modeling and text analysis. Unigrams, bigrams, and trigrams capture local word patterns and co-occurrence statistics.
Understanding N-gram
An N-gram is a contiguous sequence of N items from a given text, where items are typically words or characters. Unigrams (N=1) are single words, bigrams (N=2) are pairs of consecutive words, and trigrams (N=3) are sequences of three. Before the deep learning era, N-gram language models were the dominant approach in natural language processing, estimating the probability of the next word based on the preceding N-1 words. N-grams remain useful in modern applications for feature extraction in text classification, spell checking, keyboard prediction on mobile devices, and as baseline comparisons for neural language models. They also serve as the foundation for evaluation metrics like BLEU scores used in machine translation. While transformers have largely surpassed N-gram models in capability, understanding N-grams provides essential intuition about how language models capture sequential patterns.
Category
Natural Language Processing
Is AI recommending your brand?
Find out if ChatGPT, Perplexity, and Gemini mention you when people search your industry.
Check your brand — $9Related Natural Language Processing Terms
Abstractive Summarization
Abstractive summarization generates new text that captures the key points of a longer document, rather than simply extracting existing sentences. It requires deep language understanding and generation capabilities.
Beam Search
Beam search is a decoding algorithm that explores multiple candidate sequences simultaneously, keeping only the top-k most promising at each step. It balances between greedy decoding and exhaustive search in text generation.
BERT
BERT (Bidirectional Encoder Representations from Transformers) is a language model developed by Google that reads text in both directions simultaneously. BERT revolutionized NLP by enabling deep bidirectional pre-training for language understanding tasks.
Bigram
A bigram is a contiguous sequence of two items (typically words or characters) from a given text. Bigram models estimate the probability of a word based on the immediately preceding word.
Byte Pair Encoding
Byte Pair Encoding (BPE) is a subword tokenization algorithm that iteratively merges the most frequent pairs of characters or character sequences. BPE is widely used in modern language models to handle rare words and multilingual text.
Corpus
A corpus is a large, structured collection of text documents used for training and evaluating natural language processing models. The quality and diversity of a training corpus significantly impacts model performance.
Extractive Summarization
Extractive summarization selects and combines the most important sentences directly from a source document to create a summary. It preserves the original wording but may lack the coherence of abstractive approaches.
Grounding
Grounding in AI refers to connecting a model's language understanding to real-world knowledge, data, or sensory experience. Grounded AI systems produce more factual and contextually relevant outputs.