Edit Distance Based Curriculum Learning for Paraphrase Generation
Curriculum learning has improved the quality of neural machine translation, where only source-side features are considered in the metrics to determine the difficulty of translation. In this study, we apply curriculum learning to paraphrase generation for the first time. Different from machine translation, paraphrase generation allows a certain level of discrepancy in semantics between source and target, which results in diverse transformations from lexical substitution to reordering of clauses. Hence, the difficulty of transformations requires considering both source and target contexts. Experiments on formality transfer using GYAFC showed that our curriculum learning with edit distance improves the quality of paraphrase generation. Additionally, the proposed method improves the quality of difficult samples, which was not possible for previous methods.
Code (0)
등록된 구현이 없습니다.
Tasks
Machine TranslationParaphrase GenerationTranslationSimilar Papers 제목 키워드 기반
Neural-Driven Multi-criteria Tree Search for Paraphrase Generation
A good paraphrase is semantically similar to the original sentence but it must be also well formed, and syntactically different to ensure diversity. To deal with this trade-off, we propose to cast the paraphrase generati…
DiversityParaphrase GenerationSentenceText GenerationParaphrase Generation by Learning How to Edit from Samples
Neural sequence to sequence text generation has been proved to be a viable approach to paraphrase generation. Despite promising results, paraphrases generated by these models mostly suffer from lack of quality and divers…
DiversityParaphrase GenerationRetrievalSentence+1PCC: Paraphrasing with Bottom-k Sampling and Cyclic Learning for Curriculum Data Augmentation
Curriculum Data Augmentation (CDA) improves neural models by presenting synthetic data with increasing difficulties from easy to hard. However, traditional CDA simply treats the ratio of word perturbation as the difficul…
Data AugmentationDialogue GenerationFew-Shot Text ClassificationParaphrase Generation+2Neural-Driven Search-Based Paraphrase Generation
We study a search-based paraphrase generation scheme where candidate paraphrases are generated by iterated transformations from the original sentence and evaluated in terms of syntax quality, semantic distance, and lexic…
Paraphrase GenerationSentenceDictionary-Guided Editing Networks for Paraphrase Generation
An intuitive way for a human to write paraphrase sentences is to replace words or phrases in the original sentence with their corresponding synonyms and make necessary changes to ensure the new sentences are fluent and g…
Paraphrase GenerationSentence