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.
Understanding Bigram
Bigrams are the simplest multi-word unit in natural language processing, consisting of two consecutive tokens extracted from a text sequence, and they form the foundation of n-gram language modeling. A bigram model estimates the probability of a word by conditioning only on the single word that immediately precedes it, applying the Markov assumption that the future depends only on the present. For the sentence "the cat sat," the bigrams are "the cat" and "cat sat." Despite their simplicity, bigrams capture important local co-occurrence patterns useful for tasks like text classification, spell checking, and basic language generation. Bigram frequency analysis helps identify common phrases and collocations in a corpus. However, bigrams cannot capture long-range dependencies in language, which is why modern systems have moved toward attention mechanism-based architectures like transformers. Byte pair encoding, another subword technique, also starts from character-level pairs but uses them for tokenization rather than probabilistic modeling.
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.
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.
Language Model
A language model is an AI system that learns the probability distribution of sequences of words in a language. Modern language models like GPT and Claude can generate text, answer questions, and perform complex reasoning.