English

Smoothing and Shrinking the Sparse Seq2Seq Search Space

Computation and Language 2021-03-19 v1

Abstract

Current sequence-to-sequence models are trained to minimize cross-entropy and use softmax to compute the locally normalized probabilities over target sequences. While this setup has led to strong results in a variety of tasks, one unsatisfying aspect is its length bias: models give high scores to short, inadequate hypotheses and often make the empty string the argmax -- the so-called cat got your tongue problem. Recently proposed entmax-based sparse sequence-to-sequence models present a possible solution, since they can shrink the search space by assigning zero probability to bad hypotheses, but their ability to handle word-level tasks with transformers has never been tested. In this work, we show that entmax-based models effectively solve the cat got your tongue problem, removing a major source of model error for neural machine translation. In addition, we generalize label smoothing, a critical regularization technique, to the broader family of Fenchel-Young losses, which includes both cross-entropy and the entmax losses. Our resulting label-smoothed entmax loss models set a new state of the art on multilingual grapheme-to-phoneme conversion and deliver improvements and better calibration properties on cross-lingual morphological inflection and machine translation for 6 language pairs.

Keywords

Cite

@article{arxiv.2103.10291,
  title  = {Smoothing and Shrinking the Sparse Seq2Seq Search Space},
  author = {Ben Peters and André F. T. Martins},
  journal= {arXiv preprint arXiv:2103.10291},
  year   = {2021}
}

Comments

NAACL 2021

R2 v1 2026-06-24T00:19:12.082Z