Structural Embedding of Syntactic Trees for Machine Comprehension

2017/03/02 by Rui Liu, Liu, Rui, Junjie Hu +7 · 2 citations
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Multimodal Machine Learning Applications #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.1703.00572

openalex publication_date 2017/03/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Cited by

• Adversarial Examples for Evaluating Reading Comprehension Systems
• Making Neural Machine Reading Comprehension Faster

Related

• Top-down Tree Structured Decoding with Syntactic Connections for Neural Machine Translation and Parsing
• A Fast Unified Model for Parsing and Sentence Understanding
• Unsupervised Learning of Explainable Parse Trees for Improved Generalisation
• Probing for Constituency Structure in Neural Language Models
• Exploiting Syntactic Structure for Better Language Modeling: A Syntactic Distance Approach