DeepAI AI Chat
Log In Sign Up

ConRPG: Paraphrase Generation using Contexts as Regularizer

by   Yuxian Meng, et al.
Zhejiang University
Institute of Computing Technology, Chinese Academy of Sciences
Peking University

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.


page 1

page 2

page 3

page 4


Paraphrase Generation as Unsupervised Machine Translation

In this paper, we propose a new paradigm for paraphrase generation by tr...

Sentence Similarity Based on Contexts

Existing methods to measure sentence similarity are faced with two chall...

Triangular Bidword Generation for Sponsored Search Auction

Sponsored search auction is a crucial component of modern search engines...

Utterance Pair Scoring for Noisy Dialogue Data Filtering

Filtering noisy training data is one of the key approaches to improving ...

Lessons Learned Addressing Dataset Bias in Model-Based Candidate Generation at Twitter

Traditionally, heuristic methods are used to generate candidates for lar...

Novelty Controlled Paraphrase Generation with Retrieval Augmented Conditional Prompt Tuning

Paraphrase generation is a fundamental and long-standing task in natural...