Token
A token is the basic unit of text that a language model processes, which can be a word, subword, or character depending on the tokenizer. GPT-4 processes text in tokens, with roughly 4 characters per token in English.
Understanding Token
A token is the basic unit of text that language models process, which may represent a complete word, a subword fragment, a single character, or a punctuation mark. Tokenization algorithms like Byte Pair Encoding break text into these units, creating the vocabulary that defines what a model can read and generate. The token count of a prompt directly impacts processing cost, latency, and context window usage in commercial AI APIs. For example, the word "understanding" might be split into tokens like "under" and "standing," while common words like "the" remain single tokens. Understanding token economics is essential for managing costs when building applications with large language models, as pricing is typically based on input and output token counts. Different models use different tokenizers, leading to varying token counts for the same text.
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.