Option Comparison Network for Multiple-choice Reading Comprehension

By Qiu Ran, Peng Li, Weiwei Hu, Jie Zhou. 2019

63 citations recorded by the source corpus.

Multiple-choice reading comprehension (MCRC) is the task of selecting the correct answer from multiple options given a question and an article. Existing MCRC models typically either read each option independently or compute a fixed-length representation for each option before comparing them. However, humans typically compare the options at multiple-granularity level before reading the article in detail to make reasoning more efficient. Mimicking humans, we propose an option comparison network (OCN) for MCRC which compares options at word-level to better identify their correlations to help reasoning. Specially, each option is encoded into a vector sequence using a skimmer to retain fine-grained information as much as possible. An attention mechanism is leveraged to compare these sequences vector-by-vector to identify more subtle correlations between options, which is potentially valuable for reasoning. Experimental results on the human English exam MCRC dataset RACE show that our model outperforms existing methods significantly. Moreover, it is also the first model that surpasses Amazon Mechanical Turker performance on the whole dataset.

Subfields: Artificial Intelligence, 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 Artificial Intelligence

1. Zhuosheng Zhang
2. Hai Zhao
3. Ting-Wei Liu
4. Bing Qin
5. Yiming Cui
6. Zhao Hai
7. Shijin Wang
8. Wanxiang Che

In Natural Language Processing

1. Zhuosheng Zhang
2. Hai Zhao
3. Ting-Wei Liu
4. Zhao Hai
5. Yiming Cui
6. Guoping Hu
7. Shijin Wang
8. Wanxiang Che

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”
• Pre-Training with Whole Word Masking for Chinese BERT (2019, methodology): “…SQuAD (Rajpurkar et al., 2018), CoQA (Reddy et al., 2019), QuAC (Choi et al., 2018), NaturalQuestions (Kwiatkowski et al., 2019), RACE (Lai et al., 2017), we can see that most of the top performing models are based on BERT (Cui et al., 2017; Dai et al., 2019; Zhang et al., 2019b; Ran et al., 2019).”
• Towards Generalizable Neuro-Symbolic Systems for Commonsense Question Answering (2019, methodology): “In particular, we used ConceptNet (Speer et al., 2016) and the recently-introduced ATOMIC (Sap et al., 2019) knowledge resources, integrating them with the Option Comparison Network model (OCN; Ran et al. (2019)), a recent state-of-the-art model for multiple choice QA tasks.”
• Improving Machine Reading Comprehension with Single-choice Decision and Transfer Learning (2020, background): “Generally, the matching network can be various (Ran et al., 2019; Zhang et al., 2020; Zhu et al., 2020).”
• Revisiting Pre-Trained Models for Chinese Natural Language Processing (2020, methodology): “…et al., 2019), RACE (Lai et al., 2017), we can see that most of the top-performing models are based on BERT and its variants (Dai et al., 2019; Zhang et al., 2019; Ran et al., 2019), demonstrating that pre-trained model has become a new fundamental component in natural language processing field.”
• SG-Net: Syntax-Guided Machine Reading Comprehension (2019, methodology): “RACE For RACE, we compare our model with the following latest baselines: Dual Co-Matching Network (DCMN) (Zhang et al. 2020a), Option Comparison Network (OCN) (Ran et al. 2019), Reading Strategies Model (RSM) (Sun et al. 2018), and Generative Pre-Training (GPT) (Radford et al. 2018).”