Dual Co-Matching Network for Multi-choice Reading Comprehension
arXiv:1901.09381
Abstract
Multi-choice reading comprehension is a challenging task that requires complex reasoning procedure. Given passage and question, a correct answer need to be selected from a set of candidate answers. In this paper, we propose \textbf{D}ual \textbf{C}o-\textbf{M}atching \textbf{N}etwork (\textbf{DCMN}) which model the relationship among passage, question and answer bidirectionally. Different from existing approaches which only calculate question-aware or option-aware passage representation, we calculate passage-aware question representation and passage-aware answer representation at the same time. To demonstrate the effectiveness of our model, we evaluate our model on a large-scale multiple choice machine reading comprehension dataset (i.e. RACE). Experimental result show that our proposed model achieves new state-of-the-art results.
arXiv commentarXiv admin note: text overlap with arXiv:1806.04068 by other authors
References in corpus (8)
- Teaching Machines to Read and Comprehend
- Highway Networks
- Option Comparison Network for Multiple-choice Reading Comprehension
- Multi-range Reasoning for Machine Comprehension
- Convolutional Spatial Attention Model for Reading Comprehension with Multiple-Choice Questions
- A Co-Matching Model for Multi-choice Reading Comprehension
- Evidence Sentence Extraction for Machine Reading Comprehension
- Using Natural Language Relations between Answer Choices for Machine Comprehension
Cited by in corpus (12)
- XLNet: Generalized Autoregressive Pretraining for Language Understanding
- ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
- Machine Reading Comprehension: The Role of Contextualized Language Models and Beyond
- SG-Net: Syntax-Guided Machine Reading Comprehension
- Cosmos QA: Machine Reading Comprehension with Contextual Commonsense Reasoning
- Do Multi-hop Readers Dream of Reasoning Chains?
- Effective Subword Segmentation for Text Comprehension
- Topic-Aware Multi-turn Dialogue Modeling
- GenNet : Reading Comprehension with Multiple Choice Questions using Generation and Selection model
- Deep Human Answer Understanding for Natural Reverse QA
- GLOW : Global Weighted Self-Attention Network for Web Search
- Audio-Oriented Multimodal Machine Comprehension: Task, Dataset and Model