Loading...

Predicting subjective features from questions on qa websites using BERT

Annamoradnejad, I ; Sharif University of Technology | 2020

448 Viewed
  1. Type of Document: Article
  2. DOI: 10.1109/ICWR49608.2020.9122318
  3. Publisher: Institute of Electrical and Electronics Engineers Inc , 2020
  4. Abstract:
  5. Community Question-Answering websites, such as StackOverflow and Quora, expect users to follow specific guidelines in order to maintain content quality. These systems mainly rely on community reports for assessing contents, which has serious problems, such as the slow handling of violations, the loss of normal and experienced users' time, the low quality of some reports, and discouraging feedback to new users. Therefore, with the overall goal of providing solutions for automating moderation actions in QA websites, we aim to provide a model to predict 20 quality or subjective aspects of questions in QA websites. To this end, we used data gathered by the CrowdSource team at Google Research in 2019 and fine-tuned pre-trained BERT model on our problem. Based on our evaluation, model achieved value of 0.046 for Mean-Squared-Error (MSE) after 2 epochs of training, which did not improve substantially in the next ones. Results confirm that by simple fine-tuning, we can achieve accurate models in little time and on less amount of data.11Code is available at: https://github.com/Moradnejad/Predicting-Subjective-Features-on-QA-Websites. © 2020 IEEE
  6. Keywords:
  7. BERT ; NLP ; QA Websites ; Quality Prediction ; Subjective Features ; Transfer Learning ; HTTP ; Mean square error ; Community question answering ; Content qualities ; Fine tuning ; Low qualities ; Mean squared error ; Subjective aspects ; Websites
  8. Source: 6th International Conference on Web Research, ICWR 2020, 22 April 2020 through 23 April 2020 ; 2020 , Pages 240-244
  9. URL: https://ieeexplore.ieee.org/document/9122318