Structural Embedding of Syntactic Trees for Machine Comprehension
arXiv:1703.00572
Abstract
Deep neural networks for machine comprehension typically utilizes only word or character embeddings without explicitly taking advantage of structured linguistic information such as constituency trees and dependency trees. In this paper, we propose structural embedding of syntactic trees (SEST), an algorithm framework to utilize structured information and encode them into vector representations that can boost the performance of algorithms for the machine comprehension. We evaluate our approach using a state-of-the-art neural attention model on the SQuAD dataset. Experimental results demonstrate that our model can accurately identify the syntactic boundaries of the sentences and extract answers that are syntactically coherent over the baseline methods.
References in corpus (7)
- SQuAD: 100,000+ Questions for Machine Comprehension of Text
- Dynamic Coattention Networks For Question Answering
- Machine Comprehension Using Match-LSTM and Answer Pointer
- Learning Recurrent Span Representations for Extractive Question Answering
- Multi-Perspective Context Matching for Machine Comprehension
- NewsQA: A Machine Comprehension Dataset
- End-to-End Answer Chunk Extraction and Ranking for Reading Comprehension
Cited by in corpus (8)
- Adversarial Examples for Evaluating Reading Comprehension Systems
- MEMEN: Multi-layer Embedding with Memory Networks for Machine Comprehension
- Reinforced Mnemonic Reader for Machine Reading Comprehension
- Smarnet: Teaching Machines to Read and Comprehend Like Human
- Explicit Utilization of General Knowledge in Machine Reading Comprehension
- Making Neural Machine Reading Comprehension Faster
- Keyword-based Query Comprehending via Multiple Optimized-Demand Augmentation
- A Study of the Tasks and Models in Machine Reading Comprehension