Structural Embedding of Syntactic Trees for Machine Comprehension

03/02/2017
by   Rui Liu, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/23/2018

Exploiting Rich Syntactic Information for Semantic Parsing with Graph-to-Sequence Model

Existing neural semantic parsers mainly utilize a sequence encoder, i.e....
research
01/07/2017

Structural Attention Neural Networks for improved sentiment analysis

We introduce a tree-structured attention neural network for sentences an...
research
08/07/2018

Effective Character-augmented Word Embedding for Machine Reading Comprehension

Machine reading comprehension is a task to model relationship between pa...
research
07/10/2016

Syntactic Phylogenetic Trees

In this paper we identify several serious problems that arise in the use...
research
10/14/2020

A Self-supervised Representation Learning of Sentence Structure for Authorship Attribution

Syntactic structure of sentences in a document substantially informs abo...
research
09/12/2019

Style-aware Neural Model with Application in Authorship Attribution

Writing style is a combination of consistent decisions associated with a...
research
12/23/2017

Cartesian trees and Lyndon trees

The article describes the structural and algorithmic relations between C...

Please sign up or login with your details

Forgot password? Click here to reset