Work

Data Augmentation for Cross-Domain Named Entity Recognition

Year: 2021

Type: conference-paper

Abstract: Current work in named entity recognition (NER) shows that data augmentation techniques can produce more robust models.However, most existing techniques focus on augmenting in-domain data in low-resource scenarios where annotated data is quite limited.In contrast, we study cross-domain data augmentation for the NER task.We investigate the possibility of leveraging data from highresource domains by projecting it into the lowresource domains.Specifically, we propose a novel neural architecture to transform the data representation from a high-resource to a low-resource domain by learning the patterns (e.g.style, noise, abbreviations, etc.) in the text that differentiate them and a shared feature space where both domains are aligned.We experiment with diverse datasets and show that transforming the data to the low-resource domain representation achieves significant improvements over only using data from highresource domains. 1

Source: Conference on Empirical Methods in Natural Language Processing (EMNLP)

DOI: 10.18653/v1/2021.emnlp-main.434

Authors: Shuguang Chen, Gustavo Aguilar, Leonardo Neves, Thamar Solorio

Institutions: Snap (United States), University of Houston

Language: English

Topic: Topic Modeling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funders: National Science Foundation, University of Houston

Award: RI: Small: Robust Models for Sequence Labelling in Social Media Data