Multi-Perspective Context Matching for Machine Comprehension

Abstract

Previous machine comprehension (MC) datasets are either too small to train end-to-end deep learning models, or not difficult enough to evaluate the ability of current MC techniques. The newly released SQuAD dataset alleviates these limitations, and gives us a chance to develop more realistic MC models. Based on this dataset, we propose a Multi-Perspective Context Matching (MPCM) model, which is an end-to-end system that directly predicts the answer beginning and ending points in a passage. Our model first adjusts each word-embedding vector in the passage by multiplying a relevancy weight computed against the question. Then, we encode the question and weighted passage by using bi-directional LSTMs. For each point in the passage, our model matches the context of this point against the encoded question from multiple perspectives and produces a matching vector. Given those matched vectors, we employ another bi-directional LSTM to aggregate all the information and predict the beginning and ending points. Experimental result on the test set of SQuAD shows that our model achieves a competitive result on the leaderboard.

8

References in corpus (3)

• Machine Comprehension Using Match-LSTM and Answer Pointer
• Learning Recurrent Span Representations for Extractive Question Answering
• End-to-End Answer Chunk Extraction and Ranking for Reading Comprehension

Cited by in corpus (13)

• Adversarial Examples for Evaluating Reading Comprehension Systems
• R${}^3$: Reinforced Reader-Ranker for Open-Domain Question Answering
• NewsQA: A Machine Comprehension Dataset
• MEMEN: Multi-layer Embedding with Memory Networks for Machine Comprehension
• Exploring Question Understanding and Adaptation in Neural-Network-Based Question Answering
• A Comparative Study of Word Embeddings for Reading Comprehension
• MemexQA: Visual Memex Question Answering
• $k$-Nearest Neighbor Augmented Neural Networks for Text Classification
• An Attention-Based Word-Level Interaction Model: Relation Detection for Knowledge Base Question Answering
• Two-Stage Synthesis Networks for Transfer Learning in Machine Comprehension
• Hierarchical Question Answering for Long Documents
• Keyword-based Query Comprehending via Multiple Optimized-Demand Augmentation
• An Empirical Analysis of Multiple-Turn Reasoning Strategies in Reading Comprehension Tasks