Option Comparison Network for Multiple-choice Reading Comprehension
arXiv:1903.03033
Abstract
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.
6 pages, 2 tables
References in corpus (3)
Cited by in corpus (18)
- XLNet: Generalized Autoregressive Pretraining for Language Understanding
- Text Compression-aided Transformer Encoding
- DUMA: Reading Comprehension with Transposition Thinking
- Machine Reading Comprehension: The Role of Contextualized Language Models and Beyond
- Dual Co-Matching Network for Multi-choice Reading Comprehension
- SG-Net: Syntax-Guided Machine Reading Comprehension
- Neuro-symbolic Architectures for Context Understanding
- Towards Generalizable Neuro-Symbolic Systems for Commonsense Question Answering
- Improving Machine Reading Comprehension via Adversarial Training
- Improving Machine Reading Comprehension with Single-choice Decision and Transfer Learning
- Generalizable Neuro-symbolic Systems for Commonsense Question Answering
- Channel-aware Decoupling Network for Multi-turn Dialogue Comprehension
- Using Adversarial Attacks to Reveal the Statistical Bias in Machine Reading Comprehension Models
- GenNet : Reading Comprehension with Multiple Choice Questions using Generation and Selection model
- Self-attention Comparison Module for Boosting Performance on Retrieval-based Open-Domain Dialog Systems
- Deep Human Answer Understanding for Natural Reverse QA
- NEUer at SemEval-2021 Task 4: Complete Summary Representation by Filling Answers into Question for Matching Reading Comprehension
- Human Attention during Goal-directed Reading Comprehension Relies on Task Optimization