Design Challenges and Misconceptions in Neural Sequence Labeling

06/12/2018
by   Jie Yang, et al.
0

We investigate the design challenges of constructing effective and efficient neural sequence labeling systems, by reproducing twelve neural sequence labeling models, which include most of the state-of-the-art structures, and conduct a systematic model comparison on three benchmarks (i.e. NER, Chunking, and POS tagging). Misconceptions and inconsistent conclusions in existing literature are examined and clarified under statistical experiments. In the comparison and analysis process, we reach several practical conclusions which can be useful to practitioners.

READ FULL TEXT
research
08/12/2018

Sequence Labeling: A Practical Approach

We take a practical approach to solving sequence labeling problem assumi...
research
01/25/2023

Using novel data and ensemble models to improve automated labeling of Sustainable Development Goals

A number of labeling systems based on text have been proposed to help mo...
research
08/23/2021

Analyzing the Granularity and Cost of Annotation in Clinical Sequence Labeling

Well-annotated datasets, as shown in recent top studies, are becoming mo...
research
06/14/2018

NCRF++: An Open-source Neural Sequence Labeling Toolkit

This paper describes NCRF++, a toolkit for neural sequence labeling. NCR...
research
12/05/2022

GNN-SL: Sequence Labeling Based on Nearest Examples via GNN

To better handle long-tail cases in the sequence labeling (SL) task, in ...
research
08/23/2019

Hierarchically-Refined Label Attention Network for Sequence Labeling

CRF has been used as a powerful model for statistical sequence labeling....
research
10/07/2020

OpenIE6: Iterative Grid Labeling and Coordination Analysis for Open Information Extraction

A recent state-of-the-art neural open information extraction (OpenIE) sy...

Please sign up or login with your details

Forgot password? Click here to reset