@inproceedings{fathullah-etal-2024-needs,
    title = "Who Needs Decoders? Efficient Estimation of Sequence-Level Attributes with Proxies",
    author = "Fathullah, Yassir  and
      Radmard, Puria  and
      Liusie, Adian  and
      Gales, Mark",
    editor = "Graham, Yvette  and
      Purver, Matthew",
    booktitle = "Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = mar,
    year = "2024",
    address = "St. Julian{'}s, Malta",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/Author-page-Marten-During-lu/2024.eacl-long.89/",
    pages = "1478--1496",
    abstract = "Sequence-to-sequence models often require an expensive autoregressive decoding process. However, for some downstream tasks such as out-of-distribution (OOD) detection and resource allocation, the actual decoding output is not needed, just a scalar attribute of this sequence. In such scenarios, where knowing the quality of a system`s output to predict poor performance prevails over knowing the output itself, is it possible to bypass the autoregressive decoding? We propose Non-Autoregressive Proxy (NAP) models that can efficiently predict scalar-valued sequence-level attributes. Importantly, NAPs predict these metrics directly from the encodings, avoiding the expensive decoding stage. We consider two sequence tasks: Machine Translation (MT) and Automatic Speech Recognition (ASR). In OOD for MT, NAPs outperform ensembles while being significantly faster. NAPs are also proven capable of predicting metrics such as BERTScore (MT) or word error rate (ASR). For downstream tasks, such as data filtering and resource optimization, NAPs generate performance predictions that outperform predictive uncertainty while being highly inference efficient."
}