paper-with-me

홈 › Papers

LNMap: Departures from Isomorphic Assumption in Bilingual Lexicon Induction Through Non-Linear Mapping in Latent Space

2020-04-28 · EMNLP 2020 11 · Tasnim Mohiuddin, M Saiful Bari, Shafiq Joty

Most of the successful and predominant methods for bilingual lexicon induction (BLI) are mapping-based, where a linear mapping function is learned with the assumption that the word embedding spaces of different languages exhibit similar geometric structures (i.e., approximately isomorphic). However, several recent studies have criticized this simplified assumption showing that it does not hold in general even for closely related languages. In this work, we propose a novel semi-supervised method to learn cross-lingual word embeddings for BLI. Our model is independent of the isomorphic assumption and uses nonlinear mapping in the latent space of two independently trained auto-encoders. Through extensive experiments on fifteen (15) different language pairs (in both directions) comprising resource-rich and low-resource languages from two different datasets, we demonstrate that our method outperforms existing models by a good margin. Ablation studies show the importance of different model components and the necessity of non-linear mapping.

📄 PDF Abstract BibTeX arXiv:2004.13889

Code (0)

등록된 구현이 없습니다.

Tasks

Bilingual Lexicon InductionCross-Lingual Word EmbeddingsWord Embeddings

Similar Papers 제목 키워드 기반

Word Embedding Transformation for Robust Unsupervised Bilingual Lexicon Induction

2021-05-26 · Hailong Cao, Tiejun Zhao

Great progress has been made in unsupervised bilingual lexicon induction (UBLI) by aligning the source and target word embeddings independently trained on monolingual corpora. The common assumption of most UBLI models is…

Bilingual Lexicon InductionWord Embeddings

Bilingual Lexicon Induction with Semi-supervision in Non-Isometric Embedding Spaces

2019-08-19 · ACL 2019 7 · Barun Patra, Joel Ruben Antony Moniz, Sarthak Garg, Matthew R. Gormley 외

Recent work on bilingual lexicon induction (BLI) has frequently depended either on aligned bilingual lexicons or on distribution matching, often with an assumption about the isometry of the two spaces. We propose a techn…

Bilingual Lexicon InductionWord Embeddings

BLISS in Non-Isometric Embedding Spaces

2018-09-27 · Barun Patra, Joel Ruben Antony Moniz, Sarthak Garg, Matthew R Gormley 외

Recent work on bilingual lexicon induction (BLI) has frequently depended either on aligned bilingual lexicons or on distribution matching, often with an assumption about the isometry of the two spaces. We propose a techn…

Bilingual Lexicon InductionWord Embeddings

Multi-Adversarial Learning for Cross-Lingual Word Embeddings

2020-10-16 · NAACL 2021 4 · Haozhou Wang, James Henderson, Paola Merlo

Generative adversarial networks (GANs) have succeeded in inducing cross-lingual word embeddings -- maps of matching words across languages -- without supervision. Despite these successes, GANs' performance for the diffic…

Bilingual Lexicon InductionCross-Lingual Word EmbeddingsWord Embeddings

Beyond Offline Mapping: Learning Cross Lingual Word Embeddings through Context Anchoring

2020-12-31 · Aitor Ormazabal, Mikel Artetxe, Aitor Soroa, Gorka Labaka 외

Recent research on cross-lingual word embeddings has been dominated by unsupervised mapping approaches that align monolingual embeddings. Such methods critically rely on those embeddings having a similar structure, but i…

Bilingual Lexicon InductionCross-Lingual Word EmbeddingsSelf-LearningWord Embeddings