MCR-Net: A Multi-Step Co-Interactive Relation Network for Unanswerable Questions on Machine Reading Comprehension
This addresses a key challenge in real-world QA systems where many questions are unanswerable, improving performance for applications like search engines and chatbots, though it is incremental as it builds on existing MRC methods.
The paper tackles the problem of determining when questions are unanswerable in machine reading comprehension by proposing MCR-Net, which explicitly models mutual interactions between questions and passages, achieving a remarkable improvement over BERT-style baselines on SQuAD 2.0 and DuReader datasets.
Question answering systems usually use keyword searches to retrieve potential passages related to a question, and then extract the answer from passages with the machine reading comprehension methods. However, many questions tend to be unanswerable in the real world. In this case, it is significant and challenging how the model determines when no answer is supported by the passage and abstains from answering. Most of the existing systems design a simple classifier to determine answerability implicitly without explicitly modeling mutual interaction and relation between the question and passage, leading to the poor performance for determining the unanswerable questions. To tackle this problem, we propose a Multi-Step Co-Interactive Relation Network (MCR-Net) to explicitly model the mutual interaction and locate key clues from coarse to fine by introducing a co-interactive relation module. The co-interactive relation module contains a stack of interaction and fusion blocks to continuously integrate and fuse history-guided and current-query-guided clues in an explicit way. Experiments on the SQuAD 2.0 and DuReader datasets show that our model achieves a remarkable improvement, outperforming the BERT-style baselines in literature. Visualization analysis also verifies the importance of the mutual interaction between the question and passage.