Multi-Perspective Context Matching for Machine Comprehension
arXiv:1612.04211
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 (9)
- Adam: A Method for Stochastic Optimization
- SQuAD: 100,000+ Questions for Machine Comprehension of Text
- Dynamic Coattention Networks For Question Answering
- Machine Comprehension Using Match-LSTM and Answer Pointer
- ReasoNet: Learning to Stop Reading in Machine Comprehension
- Sentence Similarity Learning by Lexical Decomposition and Composition
- Learning Recurrent Span Representations for Extractive Question Answering
- A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task
- End-to-End Answer Chunk Extraction and Ranking for Reading Comprehension
Cited by in corpus (43)
- QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension
- ReasoNet: Learning to Stop Reading in Machine Comprehension
- Adversarial Examples for Evaluating Reading Comprehension Systems
- Bilateral Multi-Perspective Matching for Natural Language Sentences
- Reading Wikipedia to Answer Open-Domain Questions
- R: Reinforced Reader-Ranker for Open-Domain Question Answering
- Exploring Graph-structured Passage Representation for Multi-hop Reading Comprehension with Graph Neural Networks
- Bi-Directional Block Self-Attention for Fast and Memory-Efficient Sequence Modeling
- NewsQA: A Machine Comprehension Dataset
- MEMEN: Multi-layer Embedding with Memory Networks for Machine Comprehension
- A Unified MRC Framework for Named Entity Recognition
- A Unified Query-based Generative Model for Question Generation and Question Answering
- Entity-Relation Extraction as Multi-Turn Question Answering
- Making Neural QA as Simple as Possible but not Simpler
- Reinforced Mnemonic Reader for Machine Reading Comprehension
- Exploring Question Understanding and Adaptation in Neural-Network-Based Question Answering
- Dice Loss for Data-imbalanced NLP Tasks
- Description Based Text Classification with Reinforcement Learning
- A Comparative Study of Word Embeddings for Reading Comprehension
- Semi-Supervised QA with Generative Domain-Adaptive Nets
- Neural Machine Reading Comprehension: Methods and Trends
- Multi-passage BERT: A Globally Normalized BERT Model for Open-domain Question Answering
- MemexQA: Visual Memex Question Answering
- Structural Embedding of Syntactic Trees for Machine Comprehension
- Ruminating Reader: Reasoning with Gated Multi-Hop Attention
- -Nearest Neighbor Augmented Neural Networks for Text Classification
- An Attention-Based Word-Level Interaction Model: Relation Detection for Knowledge Base Question Answering
- Sequence-to-Nuggets: Nested Entity Mention Detection via Anchor-Region Networks
- Two-Stage Synthesis Networks for Transfer Learning in Machine Comprehension
- Hierarchical Question Answering for Long Documents
- Making Neural Machine Reading Comprehension Faster
- Enhancing Answer Boundary Detection for Multilingual Machine Reading Comprehension
- Evaluating Rewards for Question Generation Models
- A Rigorous Study on Named Entity Recognition: Can Fine-tuning Pretrained Model Lead to the Promised Land?
- Improving Neural Question Generation using World Knowledge
- Cross-lingual Machine Reading Comprehension with Language Branch Knowledge Distillation
- Keyword-based Query Comprehending via Multiple Optimized-Demand Augmentation
- Tackling Graphical NLP problems with Graph Recurrent Networks
- Entity Synonym Discovery via Multipiece Bilateral Context Matching
- An Empirical Analysis of Multiple-Turn Reasoning Strategies in Reading Comprehension Tasks
- Query-Based Named Entity Recognition
- CAESAR: Context Awareness Enabled Summary-Attentive Reader
- Multi-Perspective Context Aggregation for Semi-supervised Cloze-style Reading Comprehension