ConRPG: Paraphrase Generation using Contexts as Regularizer

09/01/2021
by   Yuxian Meng, et al.
0

A long-standing issue with paraphrase generation is how to obtain reliable supervision signals. In this paper, we propose an unsupervised paradigm for paraphrase generation based on the assumption that the probabilities of generating two sentences with the same meaning given the same context should be the same. Inspired by this fundamental idea, we propose a pipelined system which consists of paraphrase candidate generation based on contextual language models, candidate filtering using scoring functions, and paraphrase model training based on the selected candidates. The proposed paradigm offers merits over existing paraphrase generation methods: (1) using the context regularizer on meanings, the model is able to generate massive amounts of high-quality paraphrase pairs; and (2) using human-interpretable scoring functions to select paraphrase pairs from candidates, the proposed framework provides a channel for developers to intervene with the data generation process, leading to a more controllable model. Experimental results across different tasks and datasets demonstrate that the effectiveness of the proposed model in both supervised and unsupervised setups.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/07/2021

Paraphrase Generation as Unsupervised Machine Translation

In this paper, we propose a new paradigm for paraphrase generation by tr...
research
05/17/2021

Sentence Similarity Based on Contexts

Existing methods to measure sentence similarity are faced with two chall...
research
01/27/2021

Triangular Bidword Generation for Sponsored Search Auction

Sponsored search auction is a crucial component of modern search engines...
research
05/29/2023

Text-Only Image Captioning with Multi-Context Data Generation

Text-only Image Captioning (TIC) is an approach that aims to construct a...
research
10/21/2022

Metric-guided Distillation: Distilling Knowledge from the Metric to Ranker and Retriever for Generative Commonsense Reasoning

Commonsense generation aims to generate a realistic sentence describing ...
research
03/01/2022

RMBR: A Regularized Minimum Bayes Risk Reranking Framework for Machine Translation

Beam search is the most widely used decoding method for neural machine t...

Please sign up or login with your details

Forgot password? Click here to reset