Overview

Tutorials will take place on 6th December, immediately before the ALTA and ADCS workshops. These tutorials feature advanced methods in text processing, and will be pitched to a general audience. All workshop participants are encouraged to attend, both students and staff.

Title: Active Learning ... and Beyond! 🚀

Abstract

This half-day session will take participants through situations they might face applying Natural Language Processing to real-world problems. We’ll choose a canonical task (text classification) and focus on the main issue that faces practitioners in green fields projects --- where does the data come from? Our aim is to equip participants with the theoretical background and practical skills to quickly build high-quality text classification models.

Tutorial Presentation: Ben Hachey

Tutorial Development: Ben Hachey, Will Radford, Bo Han

Part 1: From Zero to Hero

• Background: Text categorisation, annotation and crowdsourcing, reliability
• Active learning: Selectively sampling informative examples for efficient annotation
• Data programming: Starting with zero labelled examples

Part 2: Live Shared Task

• Setup: Introducing the task and the challenge
• Hack and label: Build a classifier from scratch in 60 minutes

Part 3: Wild Blue Yonder

• Report: System descriptions and scoring
• Other challenges and approaches: Labelling by description, interactive learning, deployment and monitoring, etc.