Unsupervised Parallel Sentence Extraction with Parallel Segment Detection Helps Machine Translation
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.
Code (1)
Tasks
Machine TranslationSentenceTranslationWord EmbeddingsSimilar Papers 제목 키워드 기반
Unsupervised Parallel Sentence Extraction from Comparable Corpora
Mining parallel sentences from comparable corpora is of great interest for many downstream tasks. In the BUCC 2017 shared task, systems performed well by training on gold standard parallel sentences. However, we often wa…
SentenceWord EmbeddingsParallel Sentence Extraction from Comparable Corpora with Neural Network Features
Parallel corpora are crucial for machine translation (MT), however they are quite scarce for most language pairs and domains. As comparable corpora are far more available, many studies have been conducted to extract para…
Machine TranslationSentenceTranslationA Deep Neural Network Approach To Parallel Sentence Extraction
Parallel sentence extraction is a task addressing the data sparsity problem found in multilingual natural language processing applications. We propose an end-to-end deep neural network approach to detect translational eq…
Feature EngineeringMachine TranslationSentenceTranslation+1Parallel sentences mining with transfer learning in an unsupervised setting
The quality and quantity of parallel sentences are known as very important training data for constructing neural machine translation (NMT) systems. However, these resources are not available for many low-resource languag…
Machine TranslationNMTTransfer LearningTranslationConstructing a Chinese---Japanese Parallel Corpus from Wikipedia
Parallel corpora are crucial for statistical machine translation (SMT). However, they are quite scarce for most language pairs, such as Chinese―Japanese. As comparable corpora are far more available, many studies have be…
Machine TranslationSentenceTranslation