Conversational AI

Machine Translation

The use of AI to automatically translate text or speech from one natural language to another.

Question Answering

An NLP task where a system automatically answers questions posed in natural language based on given context.

Text Generation

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

Chatbot

A software application that simulates human conversation through text or voice interactions using NLP.

Dialogue System

A computer system designed to converse with humans, encompassing task-oriented and open-domain conversation.

Top-K Sampling

A text generation strategy that restricts the model to sampling from the K most probable next tokens.

Text-to-SQL

The task of automatically converting natural language questions into executable SQL queries, enabling non-technical users to interrogate databases through conversational interfaces.

Extractive Summarisation

A summarisation technique that identifies and selects the most important sentences from a source document to compose a condensed version without generating new text.

Intent Detection

The classification of user utterances into predefined categories representing the user's goal or purpose, a fundamental component of conversational AI and chatbot systems.

Dialogue Management

The component of conversational systems that tracks conversation state, determines the next system action, and maintains coherent multi-turn interactions with users.

Techniques and architectures that enable language models to process and reason over extremely long input sequences, from tens of thousands to millions of tokens.

Bidirectional Encoder Representations from Transformers — a language model that understands context by reading text in both directions.

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

A subword tokenisation algorithm that iteratively merges the most frequent character pairs to build a vocabulary.

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

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

Training a language model to follow natural language instructions by fine-tuning on instruction-response pairs.

Identifying semantic relationships between entities mentioned in text.