paper-with-me

홈 › Papers

Precisely the Point: Adversarial Augmentations for Faithful and Informative Text Generation

2022-10-22 · Wenhao Wu, Wei Li, Jiachen Liu, Xinyan Xiao, Sujian Li, Yajuan Lyu

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.

📄 PDF Abstract BibTeX arXiv:2210.12367

Code (0)

등록된 구현이 없습니다.

Tasks

InformativenessText Generation

Methods 이 논문이 사용한 방법론

Tanh Activation 설명 없음
Sigmoid Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…
Seq2Seq Seq2Seq, or Sequence To Sequence, is a model used in sequence prediction tasks, such as language modelling and machine translation. The idea is to use one…

Similar Papers 제목 키워드 기반

An Analysis of Self-supervised Pre-training with Dependent Samples

2026-09-04 · Maximilian Fleissner, Debarghya Ghoshdastidar, Samory Kpotufe arxiv

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 Learning

Robust Neural Abstractive Summarization Systems and Evaluation against Adversarial Information

2018-10-14 · Lisa Fan, Dong Yu, Lu Wang

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 Summarization

Robust Neural Abstractive Summarization Systems and Evaluation against Adversarial Information

2018-10-14 · NIPS Workshop IRASL 2018 · Anonymous

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 Summarization

Can Pretrained Language Models Generate Persuasive, Faithful, and Informative Ad Text for Product Descriptions?

2022-05-01 · ECNLP (ACL) 2022 5 · Fajri Koto, Jey Han Lau, Timothy Baldwin

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 Generation

GPAvatar: Generalizable and Precise Head Avatar from Image(s)

2024-01-18 · Xuangeng Chu, Yu Li, Ailing Zeng, Tianyu Yang 외

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