Papers by Javier Iranzo-Sánchez

5 papers
From Simultaneous to Streaming Machine Translation by Leveraging Streaming History (2022.acl-long)

Copied to clipboard

Challenge: Streaming MT is an extension of simultaneous MT to the incremental translation of a continuous input text stream.
Approach: They propose to extend simultaneous machine translation to streaming setups by leveraging streaming history.
Outcome: The proposed system compares favorably to the best performing systems on IWSLT Translation Tasks.
Stream-level Latency Evaluation for Simultaneous Machine Translation (2021.findings-emnlp)

Copied to clipboard

Challenge: Simultaneous machine translation systems need to find a trade-off between translation quality and response time.
Approach: They propose to adapt existing translation latency measures to streaming scenarios by re-segmenting the output translation to take into account sequential nature of streaming scenarios.
Outcome: The proposed measures are evaluated on a streaming task on simulated speech translation systems.
Direct Segmentation Models for Streaming Speech Translation (2020.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to stream ST combine advances in ASR and MT to achieve high quality translations without compromising the speed of the system.
Approach: They propose to concatenate an Automatic Speech Recognition system followed by a Machine Translation system.
Outcome: The proposed models improve on the Europarl-ST dataset on the BLEU score.
VivesDebate-Speech: A Corpus of Spoken Argumentation to Leverage Audio Features for Argument Mining (2023.emnlp-main)

Copied to clipboard

Challenge: a corpus of spoken argumentation is used to leverage audio features for argument mining tasks . a vast majority of arguments-based natural language processing resources only take text features into account .
Approach: They describe a corpus of spoken argumentation created to leverage audio features for argument mining tasks.
Outcome: The proposed corpus of spoken argumentation improves when integrating audio features into the argument mining pipeline.
Going Beyond Your Expectations in Latency Metrics for Simultaneous Speech Translation (2025.findings-acl)

Copied to clipboard

Challenge: Current evaluation practices in Simultaneous Speech Translation systems involve segmenting the input audio and its translations, calculating quality and latency metrics for each segment, and averaging the results.
Approach: They propose to use the mean to estimate latency for Simultaneous Speech Translation systems to provide a better understanding of their results.
Outcome: The proposed methods can provide a better understanding of SimulST systems’ latency.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations