paper-with-me

Papers

Contrastive Representation Learning for Exemplar-Guided Paraphrase Generation

2021-09-03 · Findings (EMNLP) 2021 11 · Haoran Yang, Wai Lam, Piji Li

Exemplar-Guided Paraphrase Generation (EGPG) aims to generate a target sentence which conforms to the style of the given exemplar while encapsulating the content information of the source sentence. In this paper, we propose a new method with the goal of learning a better representation of the style andthe content. This method is mainly motivated by the recent success of contrastive learning which has demonstrated its power in unsupervised feature extraction tasks. The idea is to design two contrastive losses with respect to the content and the style by considering two problem characteristics during training. One characteristic is that the target sentence shares the same content with the source sentence, and the second characteristic is that the target sentence shares the same style with the exemplar. These two contrastive losses are incorporated into the general encoder-decoder paradigm. Experiments on two datasets, namely QQP-Pos and ParaNMT, demonstrate the effectiveness of our proposed constrastive losses.

📄 PDF Abstract BibTeX arXiv:2109.01484

Code (1)

lhryang/crl_egpg 공식 구현 pytorch

Tasks

Contrastive LearningDecoderParaphrase GenerationPOSQQPRepresentation LearningSentence

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

Syntax-guided Controlled Generation of Paraphrases

2020-05-18 · TACL 2020 1 · Ashutosh Kumar, Kabir Ahuja, Raghuram Vadapalli, Partha Talukdar

Given a sentence (e.g., "I like mangoes") and a constraint (e.g., sentiment flip), the goal of controlled text generation is to produce a sentence that adapts the input sentence to meet the requirements of the constraint…

Paraphrase GenerationSentenceText Generation

Exemplar-Controllable Paraphrasing and Translation using Bitext

2020-10-12 · Mingda Chen, Sam Wiseman, Kevin Gimpel

Most prior work on exemplar-based syntactically controlled paraphrase generation relies on automatically-constructed large-scale paraphrase datasets, which are costly to create. We sidestep this prerequisite by adapting …

Machine TranslationParaphrase GenerationTranslation

GCPG: A General Framework for Controllable Paraphrase Generation

2022-05-01 · Findings (ACL) 2022 5 · Kexin Yang, Dayiheng Liu, Wenqiang Lei, Baosong Yang 외

Controllable paraphrase generation (CPG) incorporates various external conditions to obtain desirable paraphrases. However, existing works only highlight a special condition under two indispensable aspects of CPG (i.e., …

DecoderParaphrase GenerationSentence

GCPG: A General Framework for Controllable Paraphrase Generation

2021-10-16 · ACL ARR October 2021 10 · Anonymous

Controllable paraphrase generation (CPG) incorporates various external conditions to obtain desirable paraphrases. However, existing works only highlight a special condition under two indispensable aspects of CPG (i.e., …

DecoderParaphrase GenerationSentence

Marginal Contrastive Correspondence for Guided Image Generation

2022-04-01 · CVPR 2022 1 · Fangneng Zhan, Yingchen Yu, Rongliang Wu, Jiahui Zhang 외

Exemplar-based image translation establishes dense correspondences between a conditional input and an exemplar (from two different domains) for leveraging detailed exemplar styles to achieve realistic image translation. …

Contrastive LearningImage GenerationTexture SynthesisTranslation