Machine reading comprehension (MRC), which requires a machine to answer questions based on a given context, has attracted increasing attention with the incorporation of various deep-learning techniques over the past few years. Although research on MRC based on deep learning is flourishing, there remains a lack of a comprehensive survey summarizing existing approaches and recent trends, which motivated the work presented in this article. Specifically, we give a thorough review of this research field, covering different aspects including (1) typical MRC tasks: their definitions, differences, and representative datasets; (2) the general architecture of neural MRC: the main modules and prevalent approaches to each; and (3) new trends: some emerging areas in neural MRC as well as the corresponding challenges. Finally, considering what has been achieved so far, the survey also envisages what the future may hold by discussing the open issues left to be addressed.

This paper focuses mainly on the problem of Chinese medical question answer matching, which is arguably more challenging than open-domain question answer matching in English due to the combination of its domain-restricted nature and the language-specific features of Chinese. We present an end-to-end character-level multi-scale convolutional neural framework in which character embeddings instead of word embeddings are used to avoid Chinese word segmentation in text preprocessing, and multi-scale convolutional neural networks (CNNs) are then introduced to extract contextual information from either question or answer sentences over different scales. The proposed framework can be trained with minimal human supervision and does not require any handcrafted features, rule-based patterns, or external resources. To validate our framework, we create a new text corpus, named cMedQA, by harvesting questions and answers from an online Chinese health and wellness community. The experimental results on the cMedQA dataset show that our framework significantly outperforms several strong baselines, and achieves an improvement of top-1 accuracy by up to 19%.

Machine reading comprehension (MRC) has gained increasingly wide attention over the past few years. A variety of benchmark datasets have been released, which triggers the development of quite a few MRC approaches based on deep learning techniques. However, most existing models are designed to address English MRC. When applying them directly to Chinese documents, the performance often degrades considerably because of some special characteristics of Chinese, the inevitable segmentation errors in particular. In this article, we present the RNN Transformer (R-Trans) network to tackle the Chinese MRC task. To mitigate the influence of incorrect word segmentation and mine sequential information of whole sentences, deep contextualized word representations and bidirectional Gated Recurrent Units networks are adopted in our model. Extensive experiments have been conducted on a very large scale Chinese MRC corpus, viz. the Les MMRC dataset. The results show that the proposed model outperforms the baseline and other prevalent MRC models notably, and established a new state-of-the-art record on the Les MMRC dataset.

The task of Cross-lingual Passage Re-ranking (XPR) aims to rank a list of candidate passages in multiple languages given a query, which is generally challenged by two main issues: (1) the query and passages to be ranked are often in different languages, which requires strong cross-lingual alignment, and (2) the lack of annotated data for model training and evaluation. In this article, we propose a two-stage approach to address these issues. At the first stage, we introduce the task of Cross-lingual Paraphrase Identification (XPI) as an extra pre-training to augment the alignment by leveraging a large unsupervised parallel corpus. This task aims to identify whether two sentences, which may be from different languages, have the same meaning. At the second stage, we introduce and compare three effective strategies for cross-lingual training. To verify the effectiveness of our method, we construct an XPR dataset by assembling and modifying two monolingual datasets. Experimental results show that our augmented pre-training contributes significantly to the XPR task. Besides, we directly transfer the trained model to test on out-domain data which are constructed by modifying three multi-lingual Question Answering (QA) datasets. The results demonstrate the cross-domain robustness of the proposed approach.