Revisiting paraphrase question generator using pairwise discriminator

Badri N. Patro, Dev Chauhan, Vinod K. Kurmi, Vinay P. Namboodiri

Research output: Contribution to journalArticlepeer-review

Abstract

In this paper, we propose a method for obtaining sentence-level embeddings. While the problem of obtaining word-level embeddings is very well studied, we propose a novel method for obtaining sentence-level embeddings. This is obtained by a simple method in the context of solving the paraphrase generation task. If we use a sequential encoder-decoder model for generating paraphrase, we would like the generated paraphrase to be semantically close to the original sentence. One way to ensure this is by adding constraints for true paraphrase embeddings to be close and unrelated paraphrase candidate sentence embeddings to be far. This is ensured by using a sequential pair-wise discriminator that shares weights with the encoder. This discriminator is trained with a suitable loss function. Our loss function penalizes paraphrase sentence embedding distances from being too large. This loss is used in combination with a sequential encoder-decoder network. We also validate our method by evaluating the obtained embeddings for a sentiment analysis task. The proposed method results in semantic embeddings and provide competitive results on the paraphrase generation and sentiment analysis task on standard dataset. These results are also shown to be statistically significant.

Original languageEnglish
Pages (from-to)149-161
Number of pages13
JournalNeurocomputing
Volume420
Early online date1 Sep 2020
DOIs
Publication statusPublished - 8 Jan 2021

Keywords

  • Adversarial learning
  • Discriminator
  • GAN
  • LSTM
  • Pairwise
  • Paraphrase
  • Question Generation
  • Sentiment Analysis
  • VQA

ASJC Scopus subject areas

  • Computer Science Applications
  • Cognitive Neuroscience
  • Artificial Intelligence

Cite this