Constitutional AI

Natural Language Processing

The field of AI focused on enabling computers to understand, interpret, and generate human language.

Seq2Seq Model

A neural network architecture that maps an input sequence to an output sequence, used in translation and summarisation.

Latent Dirichlet Allocation

A generative probabilistic model for discovering topics in a collection of documents.

Text Embedding

Dense vector representations of text passages that capture semantic meaning for similarity comparison and retrieval.

Semantic Search

Search technology that understands the meaning and intent behind queries rather than just matching keywords.

Vector Database

A database optimised for storing and querying high-dimensional vector embeddings for similarity search.

Natural Language Understanding

The subfield of NLP focused on machine reading comprehension and extracting meaning from text.

Natural Language Generation

The subfield of NLP concerned with producing natural language text from structured data or representations.

Document Understanding

AI systems that extract structured information from unstructured documents by combining optical character recognition, layout analysis, and natural language comprehension.

Slot Filling

The task of extracting specific parameter values from user utterances to fulfil a detected intent, such as identifying dates, locations, and names in booking requests.

Cross-Lingual Transfer

The application of models trained in one language to perform tasks in another language, leveraging shared multilingual representations learned during pre-training.

Text Embedding Model

A neural network trained to convert text passages into fixed-dimensional vectors that capture semantic meaning, enabling similarity search, clustering, and retrieval applications.

The process of automatically extracting structured information from unstructured or semi-structured text sources.

The computational study of people's opinions, emotions, and attitudes expressed in text.

The maximum amount of text a language model can consider at once when generating a response.

A security vulnerability where malicious inputs manipulate a language model into ignoring its instructions or producing unintended outputs.

Generative Pre-trained Transformer — a family of autoregressive language models that generate text by predicting the next token.

A neural network model that learns distributed word representations by predicting surrounding context words.

The automatic transcription of spoken language into written text using acoustic and language models, foundational to voice assistants and meeting transcription systems.

A text summarisation approach that generates novel sentences to capture the essential meaning of a document, rather than simply extracting and rearranging existing sentences.

AI Alignment

The research field focused on ensuring AI systems act in accordance with human values, intentions, and ethical principles.