Utilizing Bidirectional Encoder Representations from Transformers for Answer Selection
This work addresses answer selection for question answering and community question answering tasks, showing strong performance gains but is incremental as it applies an existing method to a new task.
The paper tackled the problem of answer selection by fine-tuning the pre-trained BERT model on QA and CQA datasets, resulting in maximum improvements of 13.1% and 18.7% over previous state-of-the-art methods.
Pre-training a transformer-based model for the language modeling task in a large dataset and then fine-tuning it for downstream tasks has been found very useful in recent years. One major advantage of such pre-trained language models is that they can effectively absorb the context of each word in a sentence. However, for tasks such as the answer selection task, the pre-trained language models have not been extensively used yet. To investigate their effectiveness in such tasks, in this paper, we adopt the pre-trained Bidirectional Encoder Representations from Transformer (BERT) language model and fine-tune it on two Question Answering (QA) datasets and three Community Question Answering (CQA) datasets for the answer selection task. We find that fine-tuning the BERT model for the answer selection task is very effective and observe a maximum improvement of 13.1% in the QA datasets and 18.7% in the CQA datasets compared to the previous state-of-the-art.