@misc{dalmia2021searchable,
author = {Dalmia, Siddharth and Yan, Brian and Raunak, Vikas and Metze, Florian and Watanabe, Shinji},
title = {Searchable Hidden Intermediates for End-to-End Models of Decomposable Sequence Tasks},
howpublished = {arXiv},
year = {2021},
month = {May},
abstract = {End-to-end approaches for sequence tasks are becoming increasingly popular. Yet for complex sequence tasks, like speech translation, systems that cascade several models trained on sub-tasks have shown to be superior, suggesting that the compositionality of cascaded systems simplifies learning and enables sophisticated search capabilities. In this work, we present an end-to-end framework that exploits compositionality to learn searchable hidden representations at intermediate stages of a sequence model using decomposed sub-tasks. These hidden intermediates can be improved using beam search to enhance the overall performance and can also incorporate external models at intermediate stages of the network to re-score or adapt towards out-of-domain data. One instance of the proposed framework is a Multi-Decoder model for speech translation that extracts the searchable hidden intermediates from a speech recognition sub-task. The model demonstrates the aforementioned benefits and outperforms the previous state-of-the-art by around +6 and +3 BLEU on the two test sets of Fisher-CallHome and by around +3 and +4 BLEU on the English-German and English-French test sets of MuST-C.},
url = {http://approjects.co.za/?big=en-us/research/publication/searchable-hidden-intermediates-for-end-to-end-models-of-decomposable-sequence-tasks/},
}