Exploiting Sentence Embedding for Medical Question Answering

Understand

Despite the great success of word embedding, sentence embedding remains a not-well-solved problem.

• In this paper, we present a supervised learning framework to exploit sentence embedding for the medical question answering task.
• The learning framework consists of two main parts: 1) a sentence embedding producing module, and 2) a scoring module.
• The former is developed with contextual self-attention and multi-scale techniques to encode a sentence into an embedding tensor.