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.

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.

Rumor detection is essential for building a responsible web and internet ecosystem, which has attracted significant attention from the research community. However, emerging topic rumor detection, i.e., identifying rumors at the early stages of a topic’s emergence where only limited discussions can be observed, still remains a challenge. Technically, this scenario is accompanied by the issues of data scarcity on emerging topics and the data distribution discrepancy between old topics and emerging new topic. In this paper, we propose a new framework termed LLM-driven ADversarial Example Synthesis (LADES) for emerging topic rumor detection. LADES utilizes Large Language Models (LLMs) for generating readable and contextually coherent adversarial examples. The generated adversarial examples not only expand the training set to tackle the data scarcity issue, but also act as a bridge to connect the data distribution of old and new topics. To overcome training instability in adversarial example generation, LADES introduces a gradient-free Markov Chain Monte Carlo (MCMC) sampling method. This method ensures adversarial examples are readable and contextually coherent by harnessing LLMs, while promoting effective attacks through entropy-based sampling that targets model uncertainty. To mitigate the impact of potential mislabeling in synthetic data, LADES implements a meta-mixed-learning mechanism. This mechanism dynamically adjusts the weights of synthetic adversarial examples, guided by limited labeled data from emerging topics, thereby alleviating the data noise. Extensive experiments conducted on three real-world benchmarks demonstrate that our proposed method outperforms state-of-the-art (SOTA) baselines in terms of emerging topic rumor detection.

Event extraction (EE) generally contains two subtasks: viz., event detection and argument extraction. Owing to the success of machine reading comprehension (MRC), some researchers formulate EE into MRC frameworks. However, existing MRC-based EE techniques are pipeline methods that suffer from error propagation. Moreover, the correlation between event types and argument roles is pre-defined by experts, which is time-consuming and inflexible. To avoid these issues, event detection and argument extraction are formalized as joint MRC. Different from previous methods, which just generate questions for argument roles for identified event types, questions are generated for all arguments that appear in the given sentence in our approach. Moreover, an end-to-end MRC model, JEEMRC, is proposed, which consists of an event classifier and a machine reader with a coarse-to-fine attention mechanism. Our proposed model can train two subtasks jointly to alleviate error propagation and utilizes interaction information between event types and argument roles to improve the performance of both tasks. Experiments on ACE 2005 verify that our JEEMRC achieves competitive results compared with previous work. In addition, it performs well when detecting events and extracting arguments in data-scarce scenarios.

Zejiang He, Jingyuan Huang, Menglong Lu, Zhen Huang, Shanshan Liu, Zhiliang Tian, Dongsheng Li. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Shanshan Liu, Menglong Lu, Zhen Huang, Zejiang He, Liu Liu, Zhigang Sun, Dongsheng Li. Findings of the Association for Computational Linguistics: ACL 2025. 2025.