paper-with-me

홈 › Papers

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 difficult case of distant languages is still not satisfactory. These limitations have been explained by GANs' incorrect assumption that source and target embedding spaces are related by a single linear mapping and are approximately isomorphic. We assume instead that, especially across distant languages, the mapping is only piece-wise linear, and propose a multi-adversarial learning method. This novel method induces the seed cross-lingual dictionary through multiple mappings, each induced to fit the mapping for one subspace. Our experiments on unsupervised bilingual lexicon induction show that this method improves performance over previous single-mapping methods, especially for distant languages.

📄 PDF Abstract BibTeX arXiv:2010.08432

Code (0)

등록된 구현이 없습니다.

Tasks

Bilingual Lexicon InductionCross-Lingual Word EmbeddingsWord Embeddings

Similar Papers 제목 키워드 기반

Multi-Stage Framework with Refinement Based Point Set Registration for Unsupervised Bi-Lingual Word Alignment

2022-10-01 · COLING 2022 10 · Silviu Vlad Oprea, Sourav Dutta, Haytham Assem

Cross-lingual alignment of word embeddings are important in knowledge transfer across languages, for improving machine translation and other multi-lingual applications. Current unsupervised approaches relying on learning…

Machine TranslationTransfer LearningTranslationWord Alignment+2

Adversarial Learning with Contextual Embeddings for Zero-resource Cross-lingual Classification and NER

2019-08-31 · IJCNLP 2019 11 · Phillip Keung, Yichao Lu, Vikas Bhardwaj

Contextual word embeddings (e.g. GPT, BERT, ELMo, etc.) have demonstrated state-of-the-art performance on various NLP tasks. Recent work with the multilingual version of BERT has shown that the model performs very well i…

General Classificationnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)+4

Multi-Stage Framework with Refinement based Point Set Registration for Unsupervised Bi-Lingual Word Alignment

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Cross-lingual alignment of word embeddings play an important role in knowledge transfer across languages, for improving machine translation and other multi-lingual applications. Current unsupervised approaches rely on le…

Machine TranslationSentenceTransfer LearningTranslation+3

Identifying Cognates in English-Dutch and French-Dutch by means of Orthographic Information and Cross-lingual Word Embeddings

2020-05-01 · LREC 2020 5 · Els Lefever, Sofie Labat, Pranaydeep Singh

This paper investigates the validity of combining more traditional orthographic information with cross-lingual word embeddings to identify cognate pairs in English-Dutch and French-Dutch. In a first step, lists of potent…

Cross-Lingual Word EmbeddingsWord Embeddings

Unsupervised Word Translation with Adversarial Autoencoder

2020-06-01 · CL 2020 6 · Tasnim Mohiuddin, Shafiq Joty

Crosslingual word embeddings learned from monolingual embeddings have a crucial role in many downstream tasks, ranging from machine translation to transfer learning. Adversarial training has shown impressive success in l…

Machine TranslationTransfer LearningTranslationWord Embeddings+1