End-to-End Answer Chunk Extraction and Ranking for Reading Comprehension

Yang YuWei ZhangKazi HasanMo YuBing XiangBowen Zhou

   Papers with code   Abstract  PDF

This paper proposes dynamic chunk reader (DCR), an end-to-end neural reading comprehension (RC) model that is able to extract and rank a set of answer candidates from a given document to answer questions. DCR is able to predict answers of variable lengths, whereas previous neural RC models primarily focused on predicting single tokens or entities... (read more)

Benchmarked Models

No benchmarked models yet. Click here to submit a model.