Meta Sequence Learning and Its Applications

10/04/2020 ∙ by Cheng Zhang, et al. ∙ 0

We present a meta-sequence representation of sentences and demonstrate how to use meta sequence learning to generate adequate question-answer pairs (QAPs) over a given article. A meta sequence is a sequence of vectors of semantic and syntactic tags. On a given declarative sentence, a trained model converts it to a meta sequence, finds a matched meta sequence in its learned database, and uses the corresponding meta sequence for interrogative sentence to generate QAPs. We show that, trained on a small dataset, our method generates efficiently, on the official SAT practice reading tests, a large number of syntactically and semantically correct QAPs with high accuracy.



There are no comments yet.


page 1

page 2

page 3

page 4

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.