{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/smoothing-and-shrinking-the-sparse-seq2seq","title":"Smoothing and Shrinking the Sparse Seq2Seq Search Space","arxiv_id":"2103.10291","date":"2021-03-18","proceeding":"NAACL 2021 4","authors":["Ben Peters","André F. T. Martins"],"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.","url_abs":"https://arxiv.org/abs/2103.10291v1","url_pdf":"https://arxiv.org/pdf/2103.10291v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"smoothing-and-shrinking-the-sparse-seq2seq","repo_url":"https://github.com/deep-spin/S7","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"Grapheme-to-Phoneme Conversion"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"morphological-inflection","task_name":"Morphological Inflection"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2103.10291","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}