Predicting Issue Types with seBERT

05/03/2022

∙

Pre-trained transformer models are the current state-of-the-art for natural language models processing. seBERT is such a model, that was developed based on the BERT architecture, but trained from scratch with software engineering data. We fine-tuned this model for the NLBSE challenge for the task of issue type prediction. Our model dominates the baseline fastText for all three issue types in both recall and precisio to achieve an overall F1-score of 85.7 an increase of 4.1

READ FULL TEXT

Predicting Issue Types with seBERT

MIPT-NSU-UTMN at SemEval-2021 Task 5: Ensembling Learning with Pre-trained Language Models for Toxic Spans Detection

Myers-Briggs Personality Classification and Personality-Specific Language Generation Using Pre-trained Language Models

Continuous Active Learning Using Pretrained Transformers

Multilinguals at SemEval-2022 Task 11: Transformer Based Architecture for Complex NER

CatIss: An Intelligent Tool for Categorizing Issues Reports using Transformers

Finding Stakeholder-Material Information from 10-K Reports using Fine-Tuned BERT and LSTM Models

Aspect-Based API Review Classification: How Far Can Pre-Trained Transformer Model Go?

Predicting Issue Types with seBERT

Related Research

MIPT-NSU-UTMN at SemEval-2021 Task 5: Ensembling Learning with Pre-trained Language Models for Toxic Spans Detection

Myers-Briggs Personality Classification and Personality-Specific Language Generation Using Pre-trained Language Models

Continuous Active Learning Using Pretrained Transformers

Multilinguals at SemEval-2022 Task 11: Transformer Based Architecture for Complex NER

CatIss: An Intelligent Tool for Categorizing Issues Reports using Transformers

Finding Stakeholder-Material Information from 10-K Reports using Fine-Tuned BERT and LSTM Models

Aspect-Based API Review Classification: How Far Can Pre-Trained Transformer Model Go?