DeepAI AI Chat
Log In Sign Up

Overcoming Practical Issues of Deep Active Learning and its Applications on Named Entity Recognition

11/17/2019
by   Haw-Shiuan Chang, et al.
University of Massachusetts Amherst
Chan Zuckerberg Initiative LLC
9

Existing deep active learning algorithms achieve impressive sampling efficiency on natural language processing tasks. However, they exhibit several weaknesses in practice, including (a) inability to use uncertainty sampling with black-box models, (b) lack of robustness to noise in labeling, (c) lack of transparency. In response, we propose a transparent batch active sampling framework by estimating the error decay curves of multiple feature-defined subsets of the data. Experiments on four named entity recognition (NER) tasks demonstrate that the proposed methods significantly outperform diversification-based methods for black-box NER taggers and can make the sampling process more robust to labeling noise when combined with uncertainty-based methods. Furthermore, the analysis of experimental results sheds light on the weaknesses of different active sampling strategies, and when traditional uncertainty-based or diversification-based methods can be expected to work well.

READ FULL TEXT
07/19/2017

Deep Active Learning for Named Entity Recognition

Deep neural networks have advanced the state of the art in named entity ...
01/08/2020

LTP: A New Active Learning Strategy for Bert-CRF Based Named Entity Recognition

In recent years, deep learning has achieved great success in many natura...
01/25/2021

Recent Trends in Named Entity Recognition (NER)

The availability of large amounts of computer-readable textual data and ...
01/24/2022

BTPK-based learning: An Interpretable Method for Named Entity Recognition

Named entity recognition (NER) is an essential task in natural language ...
10/21/2022

Joint Speech Translation and Named Entity Recognition

Modern automatic translation systems aim at place the human at the cente...
08/18/2016

Active Learning for Approximation of Expensive Functions with Normal Distributed Output Uncertainty

When approximating a black-box function, sampling with active learning f...
09/26/2017

Active Learning amidst Logical Knowledge

Structured prediction is ubiquitous in applications of machine learning ...