# Classical Structured Prediction Losses for Sequence to Sequence Learning

arXiv: https://arxiv.org/abs/1711.04956 · HTML: https://mlsanity.com/paper/1711.04956/

## Key facts

- Cited by 55 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Nov 2017.

## Built on by (most cited first, 30 of 55)

- [Random Feature Attention](https://mlsanity.com/paper/2103.02143/) (2021)
- [Quark: Controllable Text Generation with Reinforced Unlearning](https://mlsanity.com/paper/2205.13636/) (2022)
- [BRIO: Bringing Order to Abstractive Summarization](https://mlsanity.com/paper/2203.16804/) (2022)
- [SimCLS: A Simple Framework for Contrastive Learning of Abstractive Summarization](https://mlsanity.com/paper/2106.01890/) (2021)
- [Calibrating Sequence likelihood Improves Conditional Language Generation](https://mlsanity.com/paper/2210.00045/) (2022)
- [High Quality Rather than High Model Probability: Minimum Bayes Risk Decoding with Neural Metrics](https://mlsanity.com/paper/2111.09388/) (2021)
- [Survey of Low-Resource Machine Translation](https://mlsanity.com/paper/2109.00486/) (2021)
- [On Learning to Summarize with Large Language Models as References](https://mlsanity.com/paper/2305.14239/) (2023)
- [RankGen: Improving Text Generation with Large Ranking Models](https://mlsanity.com/paper/2205.09726/) (2022)
- [Controlled Text Generation as Continuous Optimization with Multiple Constraints](https://mlsanity.com/paper/2108.01850/) (2021)
- [Machine Translation Decoding beyond Beam Search](https://mlsanity.com/paper/2104.05336/) (2021)
- [Quality-Aware Decoding for Neural Machine Translation](https://mlsanity.com/paper/2205.00978/) (2022)
- [Improving Large Language Model Fine-tuning for Solving Math Problems](https://mlsanity.com/paper/2310.10047/) (2023)
- [Forcing Diffuse Distributions out of Language Models](https://mlsanity.com/paper/2404.10859/) (2024)
- [Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Survey](https://mlsanity.com/paper/2104.06951/) (2021)
- [Revisiting the Weaknesses of Reinforcement Learning for Neural Machine Translation](https://mlsanity.com/paper/2106.08942/) (2021)
- [Bayesian Attention Belief Networks](https://mlsanity.com/paper/2106.05251/) (2021)
- [BLEURT Has Universal Translations: An Analysis of Automatic Metrics by Minimum Risk Training](https://mlsanity.com/paper/2307.03131/) (2023)
- [Understanding Reference Policies in Direct Preference Optimization](https://mlsanity.com/paper/2407.13709/) (2024)
- [BERTTune: Fine-Tuning Neural Machine Translation with BERTScore](https://mlsanity.com/paper/2106.02208/) (2021)
- [Sequence-Level Training for Non-Autoregressive Neural Machine Translation](https://mlsanity.com/paper/2106.08122/) (2021)
- [Modelling Latent Translations for Cross-Lingual Transfer](https://mlsanity.com/paper/2107.11353/) (2021)
- [ESRL: Efficient Sampling-based Reinforcement Learning for Sequence Generation](https://mlsanity.com/paper/2308.02223/) (2023)
- [Hierarchical classification at multiple operating points](https://mlsanity.com/paper/2210.10929/) (2022)
- [Reward Optimization for Neural Machine Translation with Learned Metrics](https://mlsanity.com/paper/2104.07541/) (2021)
- [A Call for Clarity in Beam Search: How It Works and When It Stops](https://mlsanity.com/paper/2204.05424/) (2022)
- [Large-Scale and Multi-Perspective Opinion Summarization with Diverse Review Subsets](https://mlsanity.com/paper/2310.13340/) (2023)
- [Mixed Cross Entropy Loss for Neural Machine Translation](https://mlsanity.com/paper/2106.15880/) (2021)
- [Momentum Calibration for Text Generation](https://mlsanity.com/paper/2212.04257/) (2022)
- [MAD for Robust Reinforcement Learning in Machine Translation](https://mlsanity.com/paper/2207.08583/) (2022)

## Abstract (arXiv)

There has been much recent work on training neural attention models at the sequence-level using either reinforcement learning-style methods or by optimizing the beam. In this paper, we survey a range of classical objective functions that have been widely used to train linear models for structured prediction and apply them to neural sequence to sequence models. Our experiments show that these losses can perform surprisingly well by slightly outperforming beam search optimization in a like for like setup. We also report new state of the art results on both IWSLT'14 German-English translation as well as Gigaword abstractive summarization. On the larger WMT'14 English-French translation task, sequence-level training achieves 41.5 BLEU which is on par with the state of the art.