Activity Number:
|
301
- Natural Language Processing Applications in Defense and National Security
|
Type:
|
Topic Contributed
|
Date/Time:
|
Wednesday, August 5, 2020 : 10:00 AM to 11:50 AM
|
Sponsor:
|
Section on Statistics in Defense and National Security
|
Abstract #313726
|
|
Title:
|
Few-Shot Learning for Text Applications: Exploring Authorship Identification with Small Data
|
Author(s):
|
Lauren Phillips* and Sarah Reehl and Ana Usenko
|
Companies:
|
Pacific Northwest National Laboratory and Pacific Northwest National Laboratory and Western Washington University
|
Keywords:
|
Few-shot learning;
Authorship identification;
Natural language processing;
Deep learning
|
Abstract:
|
The goal of few-shot learning is to generalize a classifier’s performance to new classes given relatively small amounts of data. It has remained a difficult challenge for machine learning algorithms and even more so when it is merged with natural language processing. Authorship identification, in particular, is a challenging problem that generally relies on large quantities of data. In this talk we introduce a dataset for few-shot authorship identification and compare results from state-of-the-art deep learning models and traditional stylometric approaches.
|
Authors who are presenting talks have a * after their name.