conftrace_

2018 EMNLP EMNLP 2018

Combining Human and Machine Transcriptions on the Zooniverse Platform

Abstract

AbstractTranscribing handwritten documents to create fully searchable texts is an essential part of the archival process. Traditional text recognition methods, such as optical character recognition (OCR), do not work on handwritten documents due to their frequent noisiness and OCR’s need for individually segmented letters. Crowdsourcing and improved machine models are two modern methods for transcribing handwritten documents.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Computer Science

🐣 Hot Topic Early Bird - optical character recognition

Authors

Daniel Hanson, Andrea Simenstad

Topics

Artificial Intelligence > Core AI > Multimodal Learning Machine Learning > Learning Types > Active Learning Machine Learning > Learning Types > Weakly Supervised Learning Computer Science > Applications > Document Analysis Machine Learning > Learning Types > Crowdsourcing

Keywords

optical character recognition text recognition human-machine collaboration handwritten document recognition handwritten document crowdsourced transcription

More from EMNLP 2018

All EMNLP 2018 papers →

FrameIt: Ontology Discovery for Noisy User-Generated Text

Using Author Embeddings to Improve Tweet Stance Classification

Low-resource named entity recognition via multi-source projection: Not quite there yet?

A Case Study on Learning a Unified Encoder of Relations

Convolutions Are All You Need (For Classifying Character Sequences)

Step or Not: Discriminator for The Real Instructions in User-generated Recipes