Skip to content
conftrace_
2021 SemEval SemEval 2021

WVOQ at SemEval-2021 Task 6: BART for Span Detection and Classification

Abstract

AbstractSimultaneous span detection and classification is a task not currently addressed in standard NLP frameworks. The present paper describes why and how an EncoderDecoder model was used to combine span detection and classification to address subtask 2 of SemEval-2021 Task 6.

Authors

Cees Roele

Topics

Artificial Intelligence > Core AI > Foundation Models Machine Learning > Core Methods > Classification

Keywords

text classification pre-trained model encoder-decoder model span classification span detection bart model
Download PDF

More from SemEval 2021

All SemEval 2021 papers →
Cisco at SemEval-2021 Task 5: What’s Toxic?: Leveraging Transformers for Multiple Toxic Span Extraction from Online Comments
MedAI at SemEval-2021 Task 5: Start-to-end Tagging Framework for Toxic Spans Detection
HamiltonDinggg at SemEval-2021 Task 5: Investigating Toxic Span Detection using RoBERTa Pre-training
HumorHunter at SemEval-2021 Task 7: Humor and Offense Recognition with Disentangled Attention
Grenzlinie at SemEval-2021 Task 7: Detecting and Rating Humor and Offense
abcbpc at SemEval-2021 Task 7: ERNIE-based Multi-task Model for Detecting and Rating Humor and Offense