A Co-Matching Model for Multi-choice Reading Comprehension

By Shuohang Wang, Mo Yu, Shiyu Chang, Jing Jiang. 2018

96 citations recorded by the source corpus.

Multi-choice reading comprehension is a challenging task, which involves the matching between a passage and a question-answer pair. This paper proposes a new co-matching approach to this problem, which jointly models whether a passage can match both a question and a candidate answer. Experimental results on the RACE dataset demonstrate that our approach achieves state-of-the-art performance.

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

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).”
Improving Question Answering with External Knowledge (2019, methodology): “…and textual information from Wikipedia by first retrieving relevant documents in Wikipedia and then running a MRC model to extract a text span from the documents based on the question (Chen et al., 2017; Wang et al., 2018b; Kratzwald and Feuerriegel, 2018; Lee et al., 2018; Lin et al., 2018).”
Dual Co-Matching Network for Multi-choice Reading Comprehension (2019, methodology): “For each { p i , Q , A } triplet, H p i ∈ R | p i |× l , H q , and H a are all representations offered by the encoder.”
Reasoning Like Program Executors (2022, methodology): “…Other lines of research did not leverage models as176 neural program executors, but instead leveraging177 program execution in inference as a reliable sanity178 guarantee for generated programs by pruning non-179 executable candidates (Wang et al., 2018b; Chen180 et al., 2019, 2021).”
Achieving Human Parity on Visual Question Answering (2021, background): “Different types of reading comprehension tasks have been proposed to make it practical, ranging from multi-choice reading comprehension [37, 81], span-based extraction [62, 83], multi-passage reading comprehension [56, 98], to multi-hop reasoning [90, 97].”
Cosmos QA: Machine Reading Comprehension with Contextual Commonsense Reasoning (2019, methodology): “Co-Matching (Wang et al., 2018b) captures the interactions between question and paragraph andarecurrentneuralnetworkbasedparagraphencodingstates.”
DREAM: A Challenge Data Set and Models for Dialogue-Based Reading Comprehension (2019, background): “• Co-Matching This state-of-the-art multiplechoice reading comprehension model explicitly treats question and answer option as two sequences and jointly matches them against a given document (Wang et al., 2018b).”
Improving Machine Reading Comprehension with General Reading Strategies (2018, methodology): “, 2018), applying hierarchical attention strategies (Zhu et al., 2018; Wang et al., 2018a), using reinforcement learning to determine the choice of multiple attention strategies (Xu et al.”
How Does NLP Benefit Legal System: A Summary of Legal Artificial Intelligence (2020, methodology): “We implemented several representative question answering models, including BiDAF (Seo et al., 2016), BERT (Devlin et al., 2019), Co-matching (Wang et al., 2018), and HAF (Zhu et al., 2018).”
Evidence Extraction for Machine Reading Comprehension with Deep Probabilistic Logic (2018, methodology): “5 Result on RACE We also evaluate our extracted evidence on other state-of-the-art machine reading models on RACE, such as co-matching11 (Wang et al., 2018).”
Multi-Matching Network for Multiple Choice Reading Comprehension (2019, background): “2017) and Hier-Co-Matching (Wang et al. 2018) are a bit similar to MMN.”
Learning to Attend On Essential Terms: An Enhanced Retriever-Reader Model for Open-domain Question Answering (2018, methodology): “, 2018) and Hierarchical Co-Matching (Wang et al., 2018a) by a relative improvement of 3.”
Evidence Sentence Extraction for Machine Reading Comprehension (2019, methodology): “We combine our evidence extractor with two recent neural readers (Wang et al., 2018b; Radford et al., 2018) and evaluate the end-to-end performance on three challenging multiple-choice MRC datasets: MultiRC (Khashabi et al.”
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.”