@inproceedings{kurfali-ostling-2019-noisy,
title = "Noisy Parallel Corpus Filtering through Projected Word Embeddings",
author = {Kurfal{\i}, Murathan and
{\"O}stling, Robert},
editor = "Bojar, Ond{\v{r}}ej and
Chatterjee, Rajen and
Federmann, Christian and
Fishel, Mark and
Graham, Yvette and
Haddow, Barry and
Huck, Matthias and
Yepes, Antonio Jimeno and
Koehn, Philipp and
Martins, Andr{\'e} and
Monz, Christof and
Negri, Matteo and
N{\'e}v{\'e}ol, Aur{\'e}lie and
Neves, Mariana and
Post, Matt and
Turchi, Marco and
Verspoor, Karin",
booktitle = "Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2)",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://preview.aclanthology.org/fix-sig-urls/W19-5438/",
doi = "10.18653/v1/W19-5438",
pages = "277--281",
abstract = "We present a very simple method for parallel text cleaning of low-resource languages, based on projection of word embeddings trained on large monolingual corpora in high-resource languages. In spite of its simplicity, we approach the strong baseline system in the downstream machine translation evaluation."
}
Markdown (Informal)
[Noisy Parallel Corpus Filtering through Projected Word Embeddings](https://preview.aclanthology.org/fix-sig-urls/W19-5438/) (Kurfalı & Östling, WMT 2019)
ACL