Precisely the Point: Adversarial Augmentations for Faithful and Informative Text Generation
Though model robustness has been extensively studied in language understanding, the robustness of Seq2Seq generation remains understudied. In this paper, we conduct the first quantitative analysis on the robustness of pre-trained Seq2Seq models. We find that even current SOTA pre-trained Seq2Seq model (BART) is still vulnerable, which leads to significant degeneration in faithfulness and informativeness for text generation tasks. This motivated us to further propose a novel adversarial augmentation framework, namely AdvSeq, for generally improving faithfulness and informativeness of Seq2Seq models via enhancing their robustness. AdvSeq automatically constructs two types of adversarial augmentations during training, including implicit adversarial samples by perturbing word representations and explicit adversarial samples by word swapping, both of which effectively improve Seq2Seq robustness. Extensive experiments on three popular text generation tasks demonstrate that AdvSeq significantly improves both the faithfulness and informativeness of Seq2Seq generation under both automatic and human evaluation settings.
Code (0)
등록된 구현이 없습니다.
Tasks
InformativenessText GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
An Analysis of Self-supervised Pre-training with Dependent Samples
Self-supervised learning relies on so-called data augmentations $φ(x)$ of unlabeled datapoints $x$ --- for example, masking random pixels in an image $x$ --- that should leave the label of $x$ invariant and are often use…
Self-Supervised LearningRobust Neural Abstractive Summarization Systems and Evaluation against Adversarial Information
Sequence-to-sequence (seq2seq) neural models have been actively investigated for abstractive summarization. Nevertheless, existing neural abstractive systems frequently generate factually incorrect summaries and are vuln…
Abstractive Text SummarizationRobust Neural Abstractive Summarization Systems and Evaluation against Adversarial Information
Sequence-to-sequence (seq2seq) neural models have been actively investigated for abstractive summarization. Nevertheless, existing neural abstractive systems frequently generate factually incorrect summaries and are vuln…
Abstractive Text SummarizationCan Pretrained Language Models Generate Persuasive, Faithful, and Informative Ad Text for Product Descriptions?
For any e-commerce service, persuasive, faithful, and informative product descriptions can attract shoppers and improve sales. While not all sellers are capable of providing such interesting descriptions, a language gene…
Text GenerationGPAvatar: Generalizable and Precise Head Avatar from Image(s)
Head avatar reconstruction, crucial for applications in virtual reality, online meetings, gaming, and film industries, has garnered substantial attention within the computer vision community. The fundamental objective of…
Neural RenderingNovel View Synthesis