The IWSLT 2018 Evaluation Campaign

By Niehues Jan, Roldano Cattoni, Stüker Sebastian, Mauro Cettolo, Marco Turchi, Marcello Federico. 2018

68 citations recorded by the source corpus.

Subfields: Natural Language Processing, Evaluation & Benchmarks

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

In Evaluation & Benchmarks

Citations in the corpus

The Bottom-up Evolution of Representations in the Transformer: A Study with Machine Translation and Language Modeling Objectives (2019, background): “very different objectives such as machine translation (MT) (Bojar et al., 2018; Niehues et al., 2018), standard left-to-right language modeling (LM) (Radford et al.”
Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned (2019, background): “The Transformer achieved state-of-the-art results in recent shared translation tasks (Bojar et al., 2018; Niehues et al., 2018).”
Europarl-ST: A Multilingual Corpus for Speech Translation of Parliamentary Debates (2019, methodology): “The latest IWSLT 2018 evaluation campaign showed that the cascade approach outperforms end-to-end models [7], but recent”
Learning Shared Semantic Space for Speech-to-Text Translation (2021, unknown): “Cascaded ST The cascaded method is a more long-standing trend in ST (Sperber et al., 2017; Jan et al., 2018).”
Sentence Boundary Augmentation for Neural Machine Translation Robustness (2020, methodology): “We use IWSLT tst2014 [10] as dev set, and test on both IWSLT-tst2015 [11] and IWSLT tst2018 [12], although our tst2018 includes only the TED talks, not the “lecture” files.”
It’s not a Non-Issue: Negation as a Source of Error in Machine Translation (2020, background): “See Penka (2015) and Horn (2010), among others, for more on the semantics, syntax, and interpretation of negation.”
A Comparative Study on End-to-End Speech to Text Translation (2019, methodology): “We have done our experiments on two ST tasks: the IWSLT TED En→De [27,28]1 and the LibriSpeech En→Fr [18,29]2.”
MuST-C: a Multilingual Speech Translation Corpus (2019, background): “First, as pointed out by (Niehues et al., 2018; Liu et al., 2018; Di Gangi et al., 2018), the use of time information brings some noise in the corpus.”
ESPnet-ST: All-in-One Speech Translation Toolkit (2020, methodology): “We also support ST-TED (Jan et al., 2018) and lowresourced Mboshi-French (Godard et al.”