Navigation auf zora.uzh.ch

Search ZORA

ZORA (Zurich Open Repository and Archive)

Maintenance: On Wednesday, February 12th 2025, maintenance work will take place on the MariaDB servers from 9:45pm to approx. 10:45pm. During this period, ZORA and JDB will be unavailable. Thank you for your understanding.

Beyond Sentence-Level End-to-End Speech Translation: Context Helps

Zhang, Biao; Titov, Ivan; Haddow, Barry; Sennrich, Rico (2021). Beyond Sentence-Level End-to-End Speech Translation: Context Helps. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), Online, 1 August 2021, ACL Anthology.

Abstract

Document-level contextual information has shown benefits to text-based machine translation, but whether and how context helps end-to-end (E2E) speech translation (ST) is still under-studied. We fill this gap through extensive experiments using a simple concatenation-based context-aware ST model, paired with adaptive feature selection on speech encodings for computational efficiency. We investigate several decoding approaches, and introduce in-model ensemble decoding which jointly performs document- and sentence-level translation using the same model. Our results on the MuST-C benchmark with Transformer demonstrate the effectiveness of context to E2E ST. Compared to sentence-level ST, context-aware ST obtains better translation quality (+0.18-2.61 BLEU), improves pronoun and homophone translation, shows better robustness to (artificial) audio segmentation errors, and reduces latency and flicker to deliver higher quality for simultaneous translation.

Additional indexing

Item Type:Conference or Workshop Item (Paper), refereed, original work
Communities & Collections:06 Faculty of Arts > Institute of Computational Linguistics
Dewey Decimal Classification:000 Computer science, knowledge & systems
410 Linguistics
Language:English
Event End Date:1 August 2021
Deposited On:08 Nov 2021 16:15
Last Modified:28 Feb 2022 08:09
Publisher:ACL Anthology
OA Status:Hybrid
Free access at:Publisher DOI. An embargo period may apply.
Publisher DOI:https://doi.org/10.18653/v1/2021.acl-long.200
Project Information:
  • Funder: H2020
  • Grant ID: 825460
  • Project Title: European Live Translator
  • Funder: SNSF
  • Grant ID: PP00P1_176727
  • Project Title: Multi-Task Learning with Multilingual Resources for Better Natural Language Understanding
Download PDF  'Beyond Sentence-Level End-to-End Speech Translation: Context Helps'.
Preview
  • Content: Published Version
  • Licence: Creative Commons: Attribution 4.0 International (CC BY 4.0)

Metadata Export

Statistics

Citations

Dimensions.ai Metrics
5 citations in Web of Science®
13 citations in Scopus®
Google Scholar™

Altmetrics

Downloads

123 downloads since deposited on 08 Nov 2021
15 downloads since 12 months
Detailed statistics

Authors, Affiliations, Collaborations

Similar Publications