Controllable Paraphrase Generation with a Syntactic Exemplar
Prior work on controllable text generation usually assumes that the controlled attribute can take on one of a small set of values known a priori. In this work, we propose a novel task, where the syntax of a generated sentence is controlled rather by a sentential exemplar. To evaluate quantitatively with standard metrics, we create a novel dataset with human annotations. We also develop a variational model with a neural module specifically designed for capturing syntactic knowledge and several multitask training objectives to promote disentangled representation learning. Empirically, the proposed model is observed to achieve improvements over baselines and learn to capture desirable characteristics.
Code (0)
등록된 구현이 없습니다.
Tasks
AttributeParaphrase GenerationRepresentation LearningSentenceText GenerationSimilar Papers 제목 키워드 기반
GCPG: A General Framework for Controllable Paraphrase Generation
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 GenerationSentenceGCPG: A General Framework for Controllable Paraphrase Generation
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 GenerationSentenceExemplar-Controllable Paraphrasing and Translation using Bitext
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 GenerationTranslationSyntax-guided Controlled Generation of Paraphrases
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 GenerationAESOP: Paraphrase Generation with Adaptive Syntactic Control
We propose to control paraphrase generation through carefully chosen target syntactic structures to generate more proper and higher quality paraphrases. Our model, AESOP, leverages a pretrained language model and adds de…
Data AugmentationLanguage ModelingLanguage ModellingParaphrase Generation+1