Multi-Matching Network for Multiple Choice Reading Comprehension

By Min Tang, Jiaran Cai, Hankui Zhuo. 2019

45 citations recorded by the source corpus.

Multiple-choice machine reading comprehension is an important and challenging task where the machine is required to select the correct answer from a set of candidate answers given passage and question. Existing approaches either match extracted evidence with candidate answers shallowly or model passage, question and candidate answers with a single paradigm of matching. In this paper, we propose Multi-Matching Network (MMN) which models the semantic relationship among passage, question and candidate answers from multiple different paradigms of matching. In our MMN model, each paradigm is inspired by how human think and designed under a unified compose-match framework. To demonstrate the effectiveness of our model, we evaluate MMN on a large-scale multiple choice machine reading comprehension dataset (i.e. RACE). Empirical results show that our proposed model achieves a significant improvement compared to strong baselines and obtains state-of-the-art results.

Subfields: Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

1. Zhuosheng Zhang
2. Dong Yu
3. Dian Yu
4. Kai Sun
5. Yuwei Wu
6. Xi Zhou
7. Xiaoping Zhou
8. Zhao Hai

Citations in the corpus

• Dual Co-Matching Network for Multi-choice Reading Comprehension (2019, background): “However, previous matching strategies fraught with obvious shortcomings (Wang et al., 2018; Tang et al., 2019; Chen et al., 2018; Ran et al., 2019) are usually unidirectional which only calculate question-aware passage representation and ignore passage-aware question representation when modeling the”
• Improving Machine Reading Comprehension with General Reading Strategies (2018, methodology): “Researchers develop a variety of methods with attention mechanisms (Chen et al., 2016; Dhingra et al., 2017; Xu et al., 2018; Tay et al., 2018; Tang et al., 2019) for improvement such as adding an elimination module (Parikh et al., 2018) or applying hierarchical attention strategies (Zhu et al.,…”
• DeepHate: Hate Speech Detection via Multi-Faceted Text Representations (2020, methodology): “The Gate Attention Network proposed by Tang et al. [38] is effective for combining two vectors.”