# Task Loss Estimation for Sequence Prediction

arXiv: https://arxiv.org/abs/1511.06456 · HTML: https://mlsanity.com/paper/1511.06456/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Nov 2015.

## Built on by (most cited first, 3 of 3)

- [Beyond In-Place Corruption: Insertion and Deletion In Denoising Probabilistic Models](https://mlsanity.com/paper/2107.07675/) (2021)
- [Learning with Algorithmic Supervision via Continuous Relaxations](https://mlsanity.com/paper/2110.05651/) (2021)
- [TO-FLOW: Efficient Continuous Normalizing Flows with Temporal Optimization adjoint with Moving Speed](https://mlsanity.com/paper/2203.10335/) (2022)

## Abstract (arXiv)

Often, the performance on a supervised machine learning task is evaluated with a emph{task loss} function that cannot be optimized directly. Examples of such loss functions include the classification error, the edit distance and the BLEU score. A common workaround for this problem is to instead optimize a emph{surrogate loss} function, such as for instance cross-entropy or hinge loss. In order for this remedy to be effective, it is important to ensure that minimization of the surrogate loss results in minimization of the task loss, a condition that we call emph{consistency with the task loss}. In this work, we propose another method for deriving differentiable surrogate losses that provably meet this requirement. We focus on the broad class of models that define a score for every input-output pair. Our idea is that this score can be interpreted as an estimate of the task loss, and that the estimation error may be used as a consistent surrogate loss. A distinct feature of such an approach is that it defines the desirable value of the score for every input-output pair. We use this property to design specialized surrogate losses for Encoder-Decoder models often used for sequence prediction tasks. In our experiment, we benchmark on the task of speech recognition. Using a new surrogate loss instead of cross-entropy to train an Encoder-Decoder speech recognizer brings a significant ~13% relative improvement in terms of Character Error Rate (CER) in the case when no extra corpora are used for language modeling.