The Death of Feature Engineering? BERT with Linguistic Features on SQuAD 2.0
This is an incremental improvement for natural language processing researchers working on question answering tasks.
The paper tackled machine reading comprehension by developing a question answering model that combines BERT with linguistic features, resulting in improvements of 2.17 EM and 2.14 F1 scores over BERT base on SQuAD 2.0, with a best model achieving 76.55 EM and 79.97 F1.
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.