Dual Co-Matching Network for Multi-choice Reading Comprehension

By Shuailiang Zhang, Zhao Hai, Yuwei Wu, Zhuosheng Zhang, Xi Zhou, Xiaoping Zhou. 2019

138 citations recorded by the source corpus.

Multi-choice reading comprehension is a challenging task to select an answer from a set of candidate options when given passage and question. Previous approaches usually only calculate question-aware passage representation and ignore passage-aware question representation when modeling the relationship between passage and question, which cannot effectively capture the relationship between passage and question. In this work, we propose dual co-matching network (DCMN) which models the relationship among passage, question and answer options bidirectionally. Besides, inspired by how humans solve multi-choice questions, we integrate two reading strategies into our model: (i) passage sentence selection that finds the most salient supporting sentences to answer the question, (ii) answer option interaction that encodes the comparison information between answer options. DCMN equipped with the two strategies (DCMN+) obtains state-of-the-art results on five multi-choice reading comprehension datasets from different domains: RACE, SemEval-2018 Task 11, ROCStories, COIN, MCTest.

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

In Natural Language Processing

Citations in the corpus

XLNet: Generalized Autoregressive Pretraining for Language Understanding (2019, background): “89 Table 6: The results of BERT on RACE are taken from [38].”
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations (2019, background): “The latter appears to be a particularly strong improvement, a jump of +17.4% absolute points over BERT (Devlin et al., 2019; Clark et al., 2019), +7.6% over XLNet (Yang et al., 2019), +6.2% over RoBERTa (Liu et al., 2019), and 5.3% over DCMI+ (Zhang et al., 2019), an ensemble of multiple models spec”
Option Comparison Network for Multiple-choice Reading Comprehension (2019, background): “…models have been proposed for MCRC and achieve promising re-sults in recent years (Chen et al., 2016; Yin et al., 2016; Trischler et al., 2016; Dhingra et al., 2017; Tay et al., 2018; Parikh et al., 2018; Zhu et al., 2018; Wang et al., 2018; Xu et al., 2017; Sun et al., 2018; Zhang et al., 2019).”
Cosmos QA: Machine Reading Comprehension with Contextual Commonsense Reasoning (2019, background): “Metrics GPT2 GPT2-FT BLEU (Papineni et al., 2002) 10.7 21.0 METEOR (Banerjee and Lavie, 2005) 7.2 8.6 ROUGE-L (Lin, 2004) 13.9 22.1 CIDEr (Vedantam et al., 2015) 0.05 0.17 BERTScore F1 (Zhang et al., 2019b) 41.9 44.5 Human 11.0% 29.0%”
Do Multi-hop Readers Dream of Reasoning Chains? (2019, unknown): “Inspired by the recent progress on the co-matching approaches for answer option selection (Wang et al., 2018; Zhang et al., 2019), we propose to adopt a similar idea for multi-hop question answering.”
Effective Subword Segmentation for Text Comprehension (2018, unknown): “The fundamental part of deep learning methods applied to natural language processing (NLP), distributed word representation, namely, word embedding, provides a basic solution to text representation for NLP tasks and has proven useful in various applications, including textual entailment [49, 56] and”
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).”
Retrospective Reader for Machine Reading Comprehension (2020, methodology): “Such an implemented ver-iﬁcation mechanism can also be as simple as an answerable threshold setting broadly used by powerful enough PLMs for quickly building readers [Devlin et al. , 2018; Zhang et al. , 2020b].”
Hierarchical Contextualized Representation for Named Entity Recognition (2019, background): “…with the development of deep neural network in a wide range of NLP tasks (He et al. 2018; He, Li, and Zhao 2019; Zhou and Zhao 2019; Xiao et al. 2019; Zhang et al. 2020a; 2020b), neural network based models build reliable NER systems without hand-crafted features or task-specific knowledge.”
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…”