The Death of Feature Engineering? BERT with Linguistic Features on SQuAD 2.0

TL;DR

This paper demonstrates that augmenting BERT with linguistic features enhances performance on the SQuAD 2.0 reading comprehension task, achieving higher accuracy and better answer localization.

Contribution

It introduces an end-to-end question answering model combining BERT with linguistic features, showing improved scores over BERT alone.

Findings

EM score improved by 2.17 points

F1 score improved by 2.14 points

Better answer localization and context understanding

Abstract

Machine reading comprehension is an essential natural language processing task, which takes into a pair of context and query and predicts the corresponding answer to query. In this project, we developed an end-to-end question answering model incorporating BERT and additional linguistic features. We conclude that the BERT base model will be improved by incorporating the features. The EM score and F1 score are improved 2.17 and 2.14 compared with BERT(base). Our best single model reaches EM score 76.55 and F1 score 79.97 in the hidden test set. Our error analysis also shows that the linguistic architecture can help model understand the context better in that it can locate answers that BERT only model predicted "No Answer" wrongly.