Context-Aware Answer Extraction in Question Answering

by   Yeon Seonwoo, et al.

Extractive QA models have shown very promising performance in predicting the correct answer to a question for a given passage. However, they sometimes result in predicting the correct answer text but in a context irrelevant to the given question. This discrepancy becomes especially important as the number of occurrences of the answer text in a passage increases. To resolve this issue, we propose BLANC (BLock AttentioN for Context prediction) based on two main ideas: context prediction as an auxiliary task in multi-task learning manner, and a block attention method that learns the context prediction task. With experiments on reading comprehension, we show that BLANC outperforms the state-of-the-art QA models, and the performance gap increases as the number of answer text occurrences increases. We also conduct an experiment of training the models using SQuAD and predicting the supporting facts on HotpotQA and show that BLANC outperforms all baseline models in this zero-shot setting.



page 6

page 7


MMM: Multi-stage Multi-task Learning for Multi-choice Reading Comprehension

Machine Reading Comprehension (MRC) for question answering (QA), which a...

Identifying Supporting Facts for Multi-hop Question Answering with Document Graph Networks

Recent advances in reading comprehension have resulted in models that su...

Cooperative Learning of Zero-Shot Machine Reading Comprehension

Pretrained language models have significantly improved the performance o...

Answering while Summarizing: Multi-task Learning for Multi-hop QA with Evidence Extraction

Question answering (QA) using textual sources such as reading comprehens...

Towards Confident Machine Reading Comprehension

There has been considerable progress on academic benchmarks for the Read...

Text Understanding with the Attention Sum Reader Network

Several large cloze-style context-question-answer datasets have been int...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.