Work

Few-Shot and Zero-Shot Learning for Historical Text Normalization

Year: 2019

Type: conference-paper

Abstract: Historical text normalization often relies on small training datasets.Recent work has shown that multi-task learning can lead to significant improvements by exploiting synergies with related datasets, but there has been no systematic study of different multitask learning architectures.This paper evaluates 63 multi-task learning configurations for sequence-to-sequence-based historical text normalization across ten datasets from eight languages, using autoencoding, grapheme-tophoneme mapping, and lemmatization as auxiliary tasks.We observe consistent, significant improvements across languages when training data for the target task is limited, but minimal or no improvements when training data is abundant.We also show that zero-shot learning outperforms the simple, but relatively strong, identity baseline.

DOI: 10.18653/v1/d19-6112

Authors: Marcel Bollmann, Natalia Korchagina, Anders Søgaard

Institutions: University of Copenhagen, University of Zurich

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Funders: European Commission, FP7 Ideas: European Research Council

Awards: Parsing low-resource languages and domains, G434337789, Morphologically-informed representations for natural language processing

OpenAlex ID: W2926029148