# BLISS: Robust Sequence-to-Sequence Learning via Self-Supervised Input Representation

arXiv: https://arxiv.org/abs/2204.07837 · HTML: https://mlsanity.com/paper/2204.07837/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 50 references that are in the map.
- First posted on arXiv 16 Apr 2022.

## Builds on (most cited first, 30 of 41)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [fairseq: A Fast, Extensible Toolkit for Sequence Modeling](https://mlsanity.com/paper/1904.01038/) (2019)
- [Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation](https://mlsanity.com/paper/1609.08144/) (2016)
- [PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization](https://mlsanity.com/paper/1912.08777/) (2019)
- [SpanBERT: Improving Pre-training by Representing and Predicting Spans](https://mlsanity.com/paper/1907.10529/) (2019)
- [EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks](https://mlsanity.com/paper/1901.11196/) (2019)
- [Non-Autoregressive Neural Machine Translation](https://mlsanity.com/paper/1711.02281/) (2017)
- [A Deep Reinforced Model for Abstractive Summarization](https://mlsanity.com/paper/1705.04304/) (2017)
- [MASS: Masked Sequence to Sequence Pre-training for Language Generation](https://mlsanity.com/paper/1905.02450/) (2019)
- [SentEval: An Evaluation Toolkit for Universal Sentence Representations](https://mlsanity.com/paper/1803.05449/) (2018)
- [Unsupervised Machine Translation Using Monolingual Corpora Only](https://mlsanity.com/paper/1711.00043/) (2017)
- [Pay Less Attention with Lightweight and Dynamic Convolutions](https://mlsanity.com/paper/1901.10430/) (2019)
- [Contextual Augmentation: Data Augmentation by Words with Paradigmatic Relations](https://mlsanity.com/paper/1805.06201/) (2018)
- [Unsupervised Neural Machine Translation](https://mlsanity.com/paper/1710.11041/) (2017)
- [StructBERT: Incorporating Language Structures into Pre-training for Deep Language Understanding](https://mlsanity.com/paper/1908.04577/) (2019)
- [Conditional BERT Contextual Augmentation](https://mlsanity.com/paper/1812.06705/) (2018)
- [Data Noising as Smoothing in Neural Network Language Models](https://mlsanity.com/paper/1703.02573/) (2017)
- [SwitchOut: an Efficient Data Augmentation Algorithm for Neural Machine Translation](https://mlsanity.com/paper/1808.07512/) (2018)
- [Sequence-Level Mixed Sample Data Augmentation](https://mlsanity.com/paper/2011.09039/) (2020)
- [AdvAug: Robust Adversarial Augmentation for Neural Machine Translation](https://mlsanity.com/paper/2006.11834/) (2020)
- [Encoder-Decoder Models Can Benefit from Pre-trained Masked Language Models in Grammatical Error Correction](https://mlsanity.com/paper/2005.00987/) (2020)
- [An Empirical Study of Incorporating Pseudo Data into Grammatical Error Correction](https://mlsanity.com/paper/1909.00502/) (2019)
- [Leveraging Monolingual Data with Self-Supervision for Multilingual Neural Machine Translation](https://mlsanity.com/paper/2005.04816/) (2020)
- [Soft Contextual Data Augmentation for Neural Machine Translation](https://mlsanity.com/paper/1905.10523/) (2019)

## Built on by (most cited first, 8 of 8)

- [A Survey of Context Engineering for Large Language Models](https://mlsanity.com/paper/2507.13334/) (2025)
- [Improving Sharpness-Aware Minimization with Fisher Mask for Better Generalization on Language Models](https://mlsanity.com/paper/2210.05497/) (2022)
- [Can Linguistic Knowledge Improve Multimodal Alignment in Vision-Language Pretraining?](https://mlsanity.com/paper/2308.12898/) (2023)
- [E2S2: Encoding-Enhanced Sequence-to-Sequence Pretraining for Language Understanding and Generation](https://mlsanity.com/paper/2205.14912/) (2022)
- [Revisiting Grammatical Error Correction Evaluation and Beyond](https://mlsanity.com/paper/2211.01635/) (2022)
- [Prompt-Learning for Cross-Lingual Relation Extraction](https://mlsanity.com/paper/2304.10354/) (2023)
- [OmniForce: On Human-Centered, Large Model Empowered and Cloud-Edge Collaborative AutoML System](https://mlsanity.com/paper/2303.00501/) (2023)
- [MPipeMoE: Memory Efficient MoE for Pre-trained Models with Adaptive Pipeline Parallelism](https://mlsanity.com/paper/2506.22175/) (2025)

## Abstract (arXiv)

Data augmentations (DA) are the cores to achieving robust sequence-to-sequence learning on various natural language processing (NLP) tasks. However, most of the DA approaches force the decoder to make predictions conditioned on the perturbed input representation, underutilizing supervised information provided by perturbed input. In this work, we propose a framework-level robust sequence-to-sequence learning approach, named BLISS, via self-supervised input representation, which has the great potential to complement the data-level augmentation approaches. The key idea is to supervise the sequence-to-sequence framework with both the textitsupervised ("inputrightarrowoutput") and textitself-supervised ("perturbed inputrightarrowinput") information. We conduct comprehensive experiments to validate the effectiveness of BLISS on various tasks, including machine translation, grammatical error correction, and text summarization. The results show that BLISS outperforms significantly the vanilla Transformer and consistently works well across tasks than the other five contrastive baselines. Extensive analyses reveal that BLISS learns robust representations and rich linguistic knowledge, confirming our claim. Source code will be released upon publication.