New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Zero-Shot Question Generation from Knowledge Graphs for Unseen Predicates and Entity Types #9

Open

flrngel opened this issue Mar 4, 2018 · 0 comments

Labels

NLP Question Generation

Owner

flrngel commented Mar 4, 2018 •

edited

Loading

https://arxiv.org/abs/1802.06842

Terms

Triple: Tuple of (subject, predicate, object)
Knowledge Base: embedding of knowledge (this paper uses TransE)

Abstract

This paper uses part-of-speech copy attention mechanism (this is term of Zero-Shot in this paper)

1. Introduction

Encoder

Concat (Input KB triple, Textual Context)
Decoder
Attention

Features

This paper solves UNK words with copying action

3. Model

3.5. Part-Of-Speech copy actions

Special Tokens(Placeholders) are replaced at post-processing step (using NLTK)

flrngel added NLP Question Generation labels

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment