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

31 Oct 2016  ·  Yang Yu, Wei zhang, Kazi Hasan, Mo Yu, Bing Xiang, Bo-Wen Zhou ·

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. DCR encodes a document and an input question with recurrent neural networks, and then applies a word-by-word attention mechanism to acquire question-aware representations for the document, followed by the generation of chunk representations and a ranking module to propose the top-ranked chunk as the answer. Experimental results show that DCR achieves state-of-the-art exact match and F1 scores on the SQuAD dataset.

PDF Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Question Answering SQuAD1.1 Dynamic Chunk Reader EM 62.499 # 187
F1 70.956 # 195
Question Answering SQuAD1.1 dev DCR EM 62.5 # 49
F1 71.2 # 51

Methods


No methods listed for this paper. Add relevant methods here