Searchable Hidden Intermediates for End-to-End Models of Decomposable Sequence Tasks
Siddharth Dalmia, Brian Yan, Vikas Raunak, Florian Metze, Shinji Watanabe
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.- Anthology ID:
- 2021.naacl-main.151
- Volume:
- Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
- Month:
- June
- Year:
- 2021
- Address:
- Online
- Editors:
- Kristina Toutanova, Anna Rumshisky, Luke Zettlemoyer, Dilek Hakkani-Tur, Iz Beltagy, Steven Bethard, Ryan Cotterell, Tanmoy Chakraborty, Yichao Zhou
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1882–1896
- Language:
- URL:
- https://aclanthology.org/2021.naacl-main.151
- DOI:
- 10.18653/v1/2021.naacl-main.151
- Cite (ACL):
- Siddharth Dalmia, Brian Yan, Vikas Raunak, Florian Metze, and Shinji Watanabe. 2021. Searchable Hidden Intermediates for End-to-End Models of Decomposable Sequence Tasks. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1882–1896, Online. Association for Computational Linguistics.
- Cite (Informal):
- Searchable Hidden Intermediates for End-to-End Models of Decomposable Sequence Tasks (Dalmia et al., NAACL 2021)
- PDF:
- https://preview.aclanthology.org/naacl-24-ws-corrections/2021.naacl-main.151.pdf