A Discriminative Latent-Variable Model for Bilingual Lexicon Induction
We introduce a novel discriminative latent variable model for bilingual lexicon induction. Our model combines the bipartite matching dictionary prior of Haghighi et al. (2008) with a representation-based approach (Artetxe et al., 2017). To train the model, we derive an efficient Viterbi EM algorithm. We provide empirical results on six language pairs under two metrics and show that the prior improves the induced bilingual lexicons. We also demonstrate how previous work may be viewed as a similarly fashioned latent-variable model, albeit with a different prior.
Code (1)
Tasks
Bilingual Lexicon InductionSimilar Papers 제목 키워드 기반
Unsupervised Bilingual Lexicon Induction via Latent Variable Models
Bilingual lexicon extraction has been studied for decades and most previous methods have relied on parallel corpora or bilingual dictionaries. Recent studies have shown that it is possible to build a bilingual dictionary…
Bilingual Lexicon InductionWord EmbeddingsA Comprehensive Analysis of Bilingual Lexicon Induction
Bilingual lexicon induction is the task of inducing word translations from monolingual corpora in two languages. In this article we present the most comprehensive analysis of bilingual lexicon induction to date. We prese…
Bilingual Lexicon InductionMachine TranslationTranslationEvaluating bilingual word embeddings on the long tail
Bilingual word embeddings are useful for bilingual lexicon induction, the task of mining translations of given words. Many studies have shown that bilingual word embeddings perform well for bilingual lexicon induction bu…
Bilingual Lexicon InductionMachine TranslationWord EmbeddingsImproving Bilingual Lexicon Induction for Low Frequency Words
This paper designs a Monolingual Lexicon Induction task and observes that two factors accompany the degraded accuracy of bilingual lexicon induction for rare words. First, a diminishing margin between similarities in low…
Bilingual Lexicon InductionBilingual Lexicon Induction for Low-Resource Languages using Graph Matching via Optimal Transport
Bilingual lexicons form a critical component of various natural language processing applications, including unsupervised and semisupervised machine translation and crosslingual information retrieval. We improve bilingual…
Bilingual Lexicon InductionGraph MatchingInformation RetrievalMachine Translation+2