Papers by Peter Polák

7 papers
Robustness of Multi-Source MT to Transcription Errors (2023.findings-acl)

Copied to clipboard

Challenge: In multilingual settings, the same content may be available in various languages via simultaneous interpreting, dubbing or subtitling.
Approach: They hypothesize that leveraging multiple sources will improve translation quality if the sources complement one another in terms of correct information they contain.
Outcome: The proposed method is robust to speech recognition errors on a 10-hour ESIC corpus.
ELITR Multilingual Live Subtitling: Demo and Strategy (2021.eacl-demos)

Copied to clipboard

Challenge: Using a prototype, we present an automatic speech translation system for live subtitling of conference speech . the system is routinely tested in recognizing English, Czech, and German speech - and presenting it simultaneously into 42 target languages.
Approach: They propose an automatic speech translation system aimed at live subtitling of conference presentations.
Outcome: The proposed system is a working prototype that is routinely tested in recognizing English, Czech, and German speech and presenting it translated simultaneously into 42 target languages.
Large Corpus of Czech Parliament Plenary Hearings (2020.lrec-1)

Copied to clipboard

Challenge: a corpus of Czech parliament plenary sessions is a valuable resource for future research . only a few public datasets are available in the Czech language . end-to-end approaches require extensive training data to produce competitive results .
Approach: They present a corpus of Czech parliament plenary sessions which is a large corpus . they combine a traditional approach with a more traditional approach .
Outcome: The proposed model architectures can be used to train and evaluate speech recognition systems on a large corpus of speech data and transcripts.
Evaluating the IWSLT2023 Speech Translation Tasks: Human Annotations, Automatic Metrics, and Segmentation (2024.lrec-main)

Copied to clipboard

Challenge: a meta-analysis of human evaluation for speech translation has not been conducted . noisy data and segmentation mismatches are challenges for automatic metrics .
Approach: They propose an evaluation strategy based on automatic resegmentation and direct assessment with segment context.
Outcome: The proposed evaluation strategy is robust and scores well-correlated with other types of human judgements.
ESPnet-ST-v2: Multipurpose Spoken Language Translation Toolkit (2023.acl-demo)

Copied to clipboard

Challenge: ESPnet-ST-v2 is a revamp of the open-source spoken language translation toolkit . it supports offline speech-to-text translation (ST), simultaneous speech- to-text (SST), and offline speech to-speech (S2ST)
Approach: They propose to revamp the open-source ESPnet-ST toolkit to support offline speech-to-text translation, simultaneous speech- to-text and offline speech to-speech translation.
Outcome: The updated version of ESPnet-ST supports offline speech-to-text translation (ST), simultaneous speech- to-text (SST), and offline speech to-speech translation (S2ST).
ALIGNMEET: A Comprehensive Tool for Meeting Annotation, Alignment, and Evaluation (2022.lrec-1)

Copied to clipboard

Challenge: Summarization is a challenging problem, and it is difficult to create, correct, and evaluate the summaries manually.
Approach: They propose an open-source tool for meeting annotation, alignment, and evaluation . the tool aims to provide an efficient and clear interface for fast annotation .
Outcome: The proposed tool is open-source and installable from PyPI.
The Green KNIGHT: Green Machine Translation with Knowledge-Distilled, Narrow, Inexpensive, Greedy, Hybrid Transformers (2025.findings-emnlp)

Copied to clipboard

Challenge: State-of-the-art neural machine translation models deliver high-quality translations at the expense of high inference latency and energy consumption.
Approach: They propose a hardware-agnostic collection of recipes to optimize translation speed and energy consumption.
Outcome: The Green KNIGHT optimizes translation speed and energy consumption with a moderate trade-off in quality.

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