Unsupervised Parallel Sentence Extraction with Parallel Segment Detection Helps Machine Translation

By Viktor Hangya, Alexander M. Fraser. 2019

31 citations recorded by the source corpus.

Mining parallel sentences from comparable corpora is important. Most previous work relies on supervised systems, which are trained on parallel data, thus their applicability is problematic in low-resource scenarios. Recent developments in building unsupervised bilingual word embeddings made it possible to mine parallel sentences based on cosine similarities of source and target language words. We show that relying only on this information is not enough, since sentences often have similar words but different meanings. We detect continuous parallel segments in sentence pair candidates and rely on them when mining parallel sentences. We show better mining accuracy on three language pairs in a standard shared task on artificial data. We also provide the first experiments showing that parallel sentences mined from real life sources improve unsupervised MT. Our code is available, we hope it will be used to support low-resource MT research.

Subfields: Artificial Intelligence, Natural Language Processing

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

In Natural Language Processing

Citations in the corpus

Cross-lingual Retrieval for Iterative Self-Supervised Training (2020, methodology): “There is also a large area of research in using sentence-level representations to mine pseudo-parallel sentence pairs [6, 13, 19, 22, 48, 49, 52].”
Self-Induced Curriculum Learning in Self-Supervised Neural Machine Translation (2020, methodology): “…sentence representations obtained from NMT systems or tailored architectures are achieving a new state-of-the-art in parallel sentence extraction and ﬁltering (Espa˜na-Bonet et al., 2017; Gr´egoire and Langlais, 2018; Artetxe and Schwenk, 2019; Hangya and Fraser, 2019; Chaudhary et al., 2019).”
Neural Machine Translation for Low-resource Languages: A Survey (2021, methodology): “Hangya and Fraser [75] used cosine similarity based Cross-Domain Similarity Local Scaling metric.”