BUCC 2017 Shared Task: a First Attempt Toward a Deep Learning Framework for Identifying Parallel Sentences in Comparable Corpora
By Francis Grégoire, Philippe Langlais. 2017
22 citations recorded by the source corpus.
This paper describes our participation in BUCC 2017 shared task: identifying parallel sentences in comparable corpora. Our goal is to leverage continuous vector representations and distributional semantics with a minimal use of external preprocessing and postprocessing tools. We report experiments that were conducted after transmitting our results.
Subfields: Artificial Intelligence, 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 Artificial Intelligence
- Edouard Grave
- Luke S. Zettlemoyer
- Armand Joulin
- Graham Neubig
- Yonatan Belinkov
- Kyunghyun Cho
- Mohit Bansal
- Furu Wei
In Natural Language Processing
- Holger Schwenk
- Yonatan Belinkov
- Armand Joulin
- Edouard Grave
- Luke S. Zettlemoyer
- Alexander M. Fraser
- Graham Neubig
- Philipp Koehn
In Evaluation & Benchmarks
- Edouard Grave
- Holger Schwenk
- Hassan Sajjad
- Houda Bouamor
- Sergey Edunov
- Viktor Hangya
- Alexander M. Fraser
- Guillaume Wenzek
Citations in the corpus
- Filtering and Mining Parallel Data in a Joint Multilingual Space (2018, methodology): “The systems RALI (Gr´egoire and Langlais, 2017) and H2 (Bouamor and Sajjad, 2018) have been already described in section 2.”
- CCMatrix: Mining Billions of High-Quality Parallel Sentences on the Web (2019, background): “Finally, related ideas have been also proposed in Bouamor and Sajjad (2018) or Gr´egoire and Langlais (2017).”
- Unsupervised Parallel Sentence Extraction with Parallel Segment Detection Helps Machine Translation (2019, background): “Following Gr´egoire and Langlais (2017), we only consider the 100 most similar target sentences for each source sentence as candidates.”
- H2@BUCC18: Parallel Sentence Extraction from Comparable Corpora Using Multilingual Sentence Embeddings (2018, background): “…each language independently, and a linear mapping is then learned to transform representations from one language to another (Mikolov et al., 2013; Grégoire and Langlais, 2017); (ii) Monolingual adaptation that relies on pre-trained embeddings of the source language when learning target…”