Cross-Lingual Transfer

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.

Constitutional AI

An approach to AI alignment where models are trained to follow a set of principles or constitution.

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.

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.

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

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

Techniques for identifying when AI language models generate plausible but factually incorrect or unsupported content.

The artificial production of human speech from text, also known as text-to-speech.

The generation of machine-readable formatted responses such as JSON, XML, or code from language models, enabling reliable integration with downstream software systems.

The process of producing coherent and contextually relevant text using AI language models.

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

Pre-Training

The initial phase of training a deep learning model on a large unlabelled corpus using self-supervised objectives, establishing general-purpose representations for downstream adaptation.