Findings of the WMT 2016 Bilingual Document Alignment Shared Task

By Christian Buck, Philipp Koehn. 2016

54 citations recorded by the source corpus.

This paper presents the results of the WMT16 Bilingual Document Alignment Shared Task. Given crawls of web sites, we asked participants to align documents that are translations of each other. 11 research groups submitted 19 systems, with a top performance of 95.0%.

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

1. Philipp Koehn
2. Graham Neubig
3. Luke S. Zettlemoyer
4. Ondrej Bojar
5. Michael Auli
6. Vishrav Chaudhary
7. Lucia Specia
8. Holger Schwenk

In Evaluation & Benchmarks

1. Philipp Koehn
2. Ondrej Bojar
3. Lucia Specia
4. Barry Haddow
5. Yvette Graham
6. Matt Post
7. Vishrav Chaudhary
8. Holger Schwenk

Citations in the corpus

• Findings of the 2016 Conference on Machine Translation (2016, methodology): “Evaluation was both automatic and manual (relative ranking and 100-point scale assessments).”
• Beyond English-Centric Multilingual Machine Translation (2020, methodology): “For example, methods aligned documents on metadata (Resnik, 1999) or sentences based on Jaccard distance or neural representations (Etchegoyhen and Azpeitia, 2016; Buck and Koehn, 2016).”
• WikiMatrix: Mining 135M Parallel Sentences in 1620 Language Pairs from Wikipedia (2019, methodology): “In the shared task for bilingual document alignment (Buck and Koehn, 2016), many participants used techniques based on n-gram or neural language models, neural translation models and bag-of-words lexical translation probabilities for scoring candidate document pairs.”
• CCMatrix: Mining Billions of High-Quality Parallel Sentences on the Web (2019, methodology): “In the shared task for bilingual document alignment (Buck and Koehn, 2016), many participants used techniques based on n -gram or neural language models, neural translation models and bag-of-words lexical translation probabilities for scoring candidate document pairs.”
• A Massive Collection of Cross-Lingual Web-Document Pairs (2019, methodology): “In the WMT-2016 bilingual document alignment shared task (Buck and Koehn, 2016a), many techniques applied retrieval and matching on translated 5-grams (Dara and Lin, 2016) to query, retrieve, and align documents.”
• Findings of the WMT 2018 Shared Task on Parallel Corpus Filtering (2018, methodology): “2 In 2016, we organized a shared task on document alignment as part of this effort (Buck and Koehn, 2016).”
• Overview of the Second BUCC Shared Task: Spotting Parallel Sentences in Comparable Corpora (2017, background): “In (Zweigenbaum et al., 2016) we showed the difference of this task to PAN’s cross-language plagiarism detection (Potthast et al., 2012), Se-mEval’s cross-language semantic text similarity (Agirre et al., 2016), and WMT’s bilingual document alignment (Buck and Koehn, 2016).”
• Findings of the WMT 2019 Shared Task on Parallel Corpus Filtering for Low-Resource Conditions (2019, background): “In previous years, as part of the Paracrawl effort, a shared task on document alignment (Buck and Koehn, 2016) and a shared task on parallel corpus filtering was organized (Koehn et al., 2018).”