A Relaxed Matching Procedure for Unsupervised BLI

Recently unsupervised Bilingual Lexicon Induction (BLI) without any parallel corpus has attracted much research interest. One of the crucial parts in methods for the BLI task is the matching procedure. Previous works impose a too strong constraint on the matching and lead to many counterintuitive translation pairings. Thus, We propose a relaxed matching procedure to find a more precise matching between two languages. We also find that aligning source and target language embedding space bidirectionally will bring significant improvement. We follow the previous iterative framework to conduct experiments. Results on standard benchmark demonstrate the effectiveness of our proposed method, which substantially outperforms previous unsupervised methods.

[1]  Pascale Fung,et al.  Compiling Bilingual Lexicon Entries From a Non-Parallel English-Chinese Corpus , 1995, VLC@ACL.

[2]  Hervé Jégou,et al.  Loss in Translation: Learning Bilingual Word Mapping with a Retrieval Criterion , 2018, EMNLP.

[3]  Dong Wang,et al.  Normalized Word Embedding and Orthogonal Transform for Bilingual Word Translation , 2015, NAACL.

[4]  Graham Neubig,et al.  Density Matching for Bilingual Word Embedding , 2019, NAACL.

[5]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[6]  Hao Wu,et al.  Wasserstein-Fisher-Rao Document Distance , 2019, ArXiv.

[7]  Marco Cuturi,et al.  Unsupervised Hyperalignment for Multilingual Word Embeddings , 2018, ICLR.

[8]  Meng Zhang,et al.  Earth Mover’s Distance Minimization for Unsupervised Bilingual Lexicon Induction , 2017, EMNLP.

[9]  Reinhard Rapp,et al.  Identifying Word Translations in Non-Parallel Texts , 1995, ACL.

[10]  Luc Lamontagne,et al.  A Robust Self-Learning Method for Fully Unsupervised Cross-Lingual Mappings of Word Embeddings: Making the Method Robustly Reproducible as Well , 2020, LREC.

[11]  Guillaume Lample,et al.  Word Translation Without Parallel Data , 2017, ICLR.

[12]  Edouard Grave,et al.  Unsupervised Alignment of Embeddings with Wasserstein Procrustes , 2018, AISTATS.

[13]  Eneko Agirre,et al.  Generalizing and Improving Bilingual Word Embedding Mappings with a Multi-Step Framework of Linear Transformations , 2018, AAAI.

[14]  Quoc V. Le,et al.  Exploiting Similarities among Languages for Machine Translation , 2013, ArXiv.

[15]  François-Xavier Vialard,et al.  Scaling algorithms for unbalanced optimal transport problems , 2017, Math. Comput..

[16]  W. Bruce Croft,et al.  Cross-lingual relevance models , 2002, SIGIR '02.

[17]  Guillaume Lample,et al.  Unsupervised Machine Translation Using Monolingual Corpora Only , 2017, ICLR.

[18]  Marco Cuturi,et al.  Sinkhorn Distances: Lightspeed Computation of Optimal Transport , 2013, NIPS.

[19]  Eneko Agirre,et al.  Learning bilingual word embeddings with (almost) no bilingual data , 2017, ACL.

[20]  Gabriel Peyré,et al.  Computational Optimal Transport , 2018, Found. Trends Mach. Learn..

[21]  Eneko Agirre,et al.  Bilingual Lexicon Induction through Unsupervised Machine Translation , 2019, ACL.

[22]  François-Xavier Vialard,et al.  An Interpolating Distance Between Optimal Transport and Fisher–Rao Metrics , 2010, Foundations of Computational Mathematics.

[23]  Tommi S. Jaakkola,et al.  Gromov-Wasserstein Alignment of Word Embedding Spaces , 2018, EMNLP.