PH-model: enhancing multi-passage machine reading comprehension with passage reranking and hierarchical information

Machine reading comprehension(MRC), which employs computers to answer questions from given passages, is a popular research field. In natural language, a natural hierarchical representation can be seen: characters, words, phrases, sentences, paragraphs, and documents. Current studies have demonstrated that hierarchical information can help machines understand natural language. However, prior works focused on the overall performance of MRC tasks without considering hierarchical information. In addition, the noise problem still has not been adequately addressed, even though many researchers have adopted the technique of passage reranking. Thus, in this paper, focusing on noise information processing and the extraction of hierarchical information, we propose a model (PH-Model) with a passage reranking framework (P) and hierarchical neural network (H) for a Chinese multi-passage MRC task. PH-Model produces more precise answers by reducing noise information and extracting hierarchical information. Experimental results on the DuReader 2.0 dataset (a large scale real-world Chinese MRC dataset) show that PH-Model outperforms the ROUGE-L and BLEU-4 baseline by 18.24% and 24.17%, respectively.

Automated summary

The study introduces the PH-Model for Chinese multi-passage MRC task, focusing on reducing noise information and extracting hierarchical information to produce more precise answers. Experimental results show that PH-Model outperforms the baseline by 18.24% and 24.17% in terms of ROUGE-L and BLEU-4 on the DuReader 2.0 dataset.