Multi-Attribute Linguistic Tuning for Controlled Paraphrase Generation
This work addresses the need for fine-grained control in paraphrase generation for applications like text editing or data augmentation, though it appears incremental as it builds on existing controllable generation models.
The paper tackles the problem of generating paraphrases with precise control over 40 linguistic attributes in English, and the result is a model that outperforms baselines in satisfying these attributes.
We present a novel approach to paraphrase generation that enables precise control and fine-tuning of 40 linguistic attributes for English. Our model is an encoder-decoder architecture that takes as input a source sentence and desired linguistic attributes, and produces paraphrases of the source that satisfy the desired attributes. To guarantee high-quality outputs at inference time, our method is equipped with a quality control mechanism that gradually adjusts the embedding of linguistic attributes to find the nearest and most attainable configuration of desired attributes for paraphrase generation. We evaluate the effectiveness of our method by comparing it to recent controllable generation models. Experimental results demonstrate that the proposed model outperforms baselines in generating paraphrases that satisfy desired linguistic attributes.