Adversarial Training for Unsupervised Bilingual Lexicon Induction

Word embeddings are well known to capture linguistic regularities of the language on which they are trained. Researchers also observe that these regularities can transfer across languages. However, previous endeavors to connect separate monolingual word embeddings typically require cross-lingual signals as supervision, either in the form of parallel corpus or seed lexicon. In this work, we show that such cross-lingual connection can actually be established without any form of supervision. We achieve this end by formulating the problem as a natural adversarial game, and investigating techniques that are crucial to successful training. We carry out evaluation on the unsupervised bilingual lexicon induction task. Even though this task appears intrinsically cross-lingual, we are able to demonstrate encouraging performance without any cross-lingual clues.

• Publication year

  2017

• Venue

  Annual Meeting of the Association for Computational Linguistics

• Publication date

  2017-07-01

• Fields of study

  Linguistics, Computer Science

• Identifiers
  DOI 10.18653/v1/P17-1179
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• GENERATIVE ADVERSARIAL NETS

  2018influential reference
• Offline bilingual word vectors, orthogonal transformations and the inverted softmax

  2017cited by this paper
• Bilingual Lexicon Induction from Non-Parallel Data with Minimal Supervision

  2017cited by this paper
• Towards Principled Methods for Training Generative Adversarial Networks

  2017cited by this paper
• f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization

  2016cited by this paper
• Ten Pairs to Tag – Multilingual POS Tagging via Coarse Mapping between Embeddings

  2016cited by this paper
• Learning principled bilingual mappings of word embeddings while preserving monolingual invariance

  2016cited by this paper
• Massively Multilingual Word Embeddings

  2016cited by this paper
• Towards cross-lingual distributed representations without parallel text trained with adversarial autoencoders

  2016cited by this paper
• Improved Techniques for Training GANs

  2016cited by this paper
• Cross-Lingual Word Representations via Spectral Graph Embeddings

  2016cited by this paper
• Inducing Bilingual Lexica From Non-Parallel Data With Earth Mover’s Distance Regularization

  2016influential reference
• Cross-lingual Models of Word Embeddings: An Empirical Comparison

  2016cited by this paper
• A Distribution-based Model to Learn Bilingual Word Embeddings

  2016influential reference
• Dual Learning for Machine Translation

  2016cited by this paper
• Amortised MAP Inference for Image Super-resolution

  2016cited by this paper
• Adversarial Deep Averaging Networks for Cross-Lingual Sentiment Classification

  2016cited by this paper
• Efficient Orthogonal Parametrisation of Recurrent Neural Networks Using Householder Reflections

  2016cited by this paper
• Learning Crosslingual Word Embeddings without Bilingual Corpora

  2016cited by this paper
• Learning in Implicit Generative Models

  2016cited by this paper
• On the Role of Seed Lexicons in Learning Bilingual Word Embeddings

  2016influential reference
• Minimally-Constrained Multilingual Embeddings via Artificial Code-Switching

  2016cited by this paper
• LORELEI Language Packs: Data, Tools, and Resources for Technology Development in Low Resource Languages

  2016cited by this paper
• Adversarial Autoencoders

  2015cited by this paper
• Deep Multilingual Correlation for Improved Word Embeddings

  2015cited by this paper
• Unifying Bayesian Inference and Vector Space Models for Improved Decipherment

  2015cited by this paper
• Simple task-specific bilingual word embeddings

  2015cited by this paper
• Trans-gram, Fast Cross-lingual Word-embeddings

  2015cited by this paper
• Domain-Adversarial Training of Neural Networks

  2015cited by this paper
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks

  2015cited by this paper
• Hubness and Pollution: Delving into Cross-Space Mapping for Zero-Shot Learning

  2015cited by this paper
• Bilingual Word Embeddings from Non-Parallel Document-Aligned Data Applied to Bilingual Lexicon Induction

  2015cited by this paper
• Bilingual Word Representations with Monolingual Quality in Mind

  2015cited by this paper
• On the universal structure of human lexical semantics

  2015cited by this paper
• Learning Cross-lingual Word Embeddings via Matrix Co-factorization

  2015cited by this paper
• Normalized Word Embedding and Orthogonal Transform for Bilingual Word Translation

  2015cited by this paper
• Adam: A Method for Stochastic Optimization

  2014cited by this paper
• An Autoencoder Approach to Learning Bilingual Word Representations

  2014cited by this paper
• Dropout: a simple way to prevent neural networks from overfitting

  2014cited by this paper
• Improving zero-shot learning by mitigating the hubness problem

  2014cited by this paper
• BilBOWA: Fast Bilingual Distributed Representations without Word Alignments

  2014cited by this paper
• Learning Bilingual Word Representations by Marginalizing Alignments

  2014cited by this paper
• Improving Vector Space Word Representations Using Multilingual Correlation

  2014cited by this paper
• Distributed Representations of Words and Phrases and their Compositionality

  2013influential reference
• Dropout Training as Adaptive Regularization

  2013cited by this paper
• Dependency-Based Decipherment for Resource-Limited Machine Translation

  2013cited by this paper
• Bilingual Word Embeddings for Phrase-Based Machine Translation

  2013cited by this paper
• Multilingual Distributed Representations without Word Alignment

  2013cited by this paper
• Combining Bilingual and Comparable Corpora for Low Resource Machine Translation

  2013cited by this paper
• Learning with Marginalized Corrupted Features

  2013cited by this paper
• Exploiting Similarities among Languages for Machine Translation

  2013influential reference
• Cross-Lingual Semantic Similarity of Words as the Similarity of Their Semantic Word Responses

  2013influential reference
• Large Scale Decipherment for Out-of-Domain Machine Translation

  2012cited by this paper
• Identifying Word Translations from Comparable Corpora Using Latent Topic Models

  2011cited by this paper
• Domain Adaptation for Machine Translation by Mining Unseen Words

  2011cited by this paper
• Learning Bilingual Lexicons from Monolingual Corpora

  2008cited by this paper
• Mining Very-Non-Parallel Corpora: Parallel Sentence and Lexicon Extraction via Bootstrapping and E

  2004cited by this paper
• A Geometric View on Bilingual Lexicon Extraction from Comparable Corpora

  2004cited by this paper
• Learning a Translation Lexicon from Monolingual Corpora

  2002cited by this paper
• Automatic Identification of Word Translations from Unrelated English and German Corpora

  1999cited by this paper
• Current address: Microsoft Research,

  year unknowncited by this paper

• Cross-Lingual Representation Alignment Through Contrastive Image-Caption Tuning

  2025cites this paper
• AZIM: Arabic-Centric Zero-Shot Inference for Multilingual Topic Modeling With Enhanced Performance on Summarized Text

  2025cites this paper
• mini-vec2vec: Scaling Universal Geometry Alignment with Linear Transformations

  2025cites this paper
• Word-level Cross-lingual Structure in Large Language Models

  2025cites this paper
• Reshaping Word Embedding Space With Monolingual Synonyms for Bilingual Lexicon Induction

  2025cites this paper
• Lost in Alignment: A Survey on Cross-Lingual Alignment Methods for Contextualized Representation

  2025cites this paper
• Middle-Layer Representation Alignment for Cross-Lingual Transfer in Fine-Tuned LLMs

  2025cites this paper
• A domain-specific cross-lingual semantic alignment learning model for low-resource languages

  2025cites this paper
• Aligning Embeddings and Geometric Random Graphs: Informational Results and Computational Approaches for the Procrustes-Wasserstein Problem

  2024cites this paper
• LinguaLIFT: An Effective Two-stage Instruction Tuning Framework for Low-Resource Language Tasks

  2024cites this paper
• SeNSe: embedding alignment via semantic anchors selection

  2024cites this paper
• Alignment of Multilingual Embeddings to Estimate Job Similarities in Online Labour Market

  2024cites this paper
• DM-BLI: Dynamic Multiple Subspaces Alignment for Unsupervised Bilingual Lexicon Induction

  2024cites this paper
• The Shape of Word Embeddings: Quantifying Non-Isometry with Topological Data Analysis

  2024cites this paper
• A survey of neural-network-based methods utilising comparable data for finding translation equivalents

  2024influential citation
• Cross-Network Embeddings Transfer for Traffic Analysis

  2024cites this paper
• Decipherment-Aware Multilingual Learning in Jointly Trained Language Models

  2024cites this paper
• Toward Cross-Lingual Social Event Detection with Hybrid Knowledge Distillation

  2024cites this paper
• TLS-WGAN-GP: A Generative Adversarial Network Model for Data-Driven Fault Root Cause Location

  2023cites this paper
• LAPCA: Language-Agnostic Pretraining with Cross-Lingual Alignment

  2023cites this paper
• Listen, Decipher and Sign: Toward Unsupervised Speech-to-Sign Language Recognition

  2023cites this paper
• ADMit: Improving NER in automotive domain with domain adversarial training and multi-task learning

  2023cites this paper
• Accessing Higher Dimensions for Unsupervised Word Translation

  2023cites this paper
• ProMap: Effective Bilingual Lexicon Induction via Language Model Prompting

  2023cites this paper
• Neural Machine Translation: A Survey of Methods used for Low Resource Languages

  2023cites this paper
• Enabling Unsupervised Neural Machine Translation with Word-level Visual Representations

  2023cites this paper
• An approach to lexicon filtering for author profiling

  2023cites this paper
• DA-DAN: A Dual Adversarial Domain Adaption Network for Unsupervised Non-overlapping Cross-domain Recommendation

  2023cites this paper
• Bilingual word embedding fusion for robust unsupervised bilingual lexicon induction

  2023cites this paper
• An Unsupervised Approach to Bilingual Lexicon Induction with Comparable Corpora

  2023cites this paper
• Few-shot Named Entity Recognition: Definition, Taxonomy and Research Directions

  2023cites this paper
• A Novel Unsupervised Approach for Cross-Lingual Word Alignment in Low Isomorphic Embedding Spaces

  2023cites this paper
• Transformer: A General Framework from Machine Translation to Others

  2023cites this paper
• MUSEDA: Multilingual Unsupervised and Supervised Embedding for Domain Adaption

  2023cites this paper
• Investigating Unsupervised Neural Machine Translation for Low-resource Language Pair English-Mizo via Lexically Enhanced Pre-trained Language Models

  2023cites this paper
• Leveraging Context Patterns for Medical Entity Classification

  2023cites this paper
• English-Manipuri Cross-Lingual Embedding: A Preliminary Study

  2023influential citation
• Hyperpolyglot LLMs: Cross-Lingual Interpretability in Token Embeddings

  2023cites this paper
• Learning bilingual word embedding for automatic text summarization in low resource language

  2023cites this paper
• Mining parallel sentences from internet with multi-view knowledge distillation for low-resource language pairs

  2023cites this paper
• GRI: Graph-based Relative Isomorphism of Word Embedding Spaces

  2023cites this paper
• Multi-Stage Framework with Refinement Based Point Set Registration for Unsupervised Bi-Lingual Word Alignment

  2022cites this paper
• Cross-lingual Feature Extraction from Monolingual Corpora for Low-resource Unsupervised Bilingual Lexicon Induction

  2022cites this paper
• Unsupervised Alignment of Distributional Word Embeddings

  2022cites this paper
• Deep Multilabel Multilingual Document Learning for Cross-Lingual Document Retrieval

  2022cites this paper
• Topic-Based Unsupervised and Supervised Dictionary Induction

  2022cites this paper
• Domain Mismatch Doesn’t Always Prevent Cross-lingual Transfer Learning

  2022cites this paper
• Aligning Word Vectors on Low-Resource Languages with Wiktionary

  2022cites this paper
• English-Malay Cross-Lingual Embedding Alignment using Bilingual Lexicon Augmentation

  2022cites this paper
• Utilizing Language-Image Pretraining for Efficient and Robust Bilingual Word Alignment

  2022cites this paper
• Robust Unsupervised Cross-Lingual Word Embedding using Domain Flow Interpolation

  2022cites this paper
• Towards Unsupervised Speech-to-Speech Translation

  2022cites this paper
• A cross-lingual sentence pair interaction feature capture model based on pseudo-corpus and multilingual embedding

  2022cites this paper
• Sub-Word Alignment is Still Useful: A Vest-Pocket Method for Enhancing Low-Resource Machine Translation

  2022cites this paper
• Robust Question Answering on Out-of-Domain Data

  2022cites this paper
• Bridging the Data Gap between Training and Inference for Unsupervised Neural Machine Translation

  2022cites this paper
• Don’t Forget Cheap Training Signals Before Building Unsupervised Bilingual Word Embeddings

  2022cites this paper
• Cross-Lingual Transfer with Class-Weighted Language-Invariant Representations

  2022cites this paper
• Unsupervised Parallel Sentences of Machine Translation for Asian Language Pairs

  2022cites this paper
• Low-resource Neural Machine Translation: Methods and Trends

  2022cites this paper
• Sub-word based unsupervised bilingual dictionary induction for Chinese-Uyghur

  2022cites this paper
• Learning Bilingual Word Embedding Mappings with Similar Words in Related Languages Using GAN

  2022cites this paper
• Understanding models understanding language

  2022cites this paper
• Inducing Generalizable and Interpretable Lexica

  2022cites this paper
• QA Domain Adaptation using Data Augmentation and Contrastive Adaptation

  2021cites this paper
• Bilingual Terminology Extraction from Comparable E-Commerce Corpora

  2021cites this paper
• Improving bilingual word embeddings mapping with monolingual context information

  2021influential citation
• Unsupervised Neural Machine Translation with Universal Grammar

  2021cites this paper
• Adversarial Domain Adaptation for Cross-lingual Information Retrieval with Multilingual BERT

  2021cites this paper
• English–Welsh Cross-Lingual Embeddings

  2021cites this paper
• Embedding Semantic Anchors to Guide Topic Models on Short Text Corpora

  2021cites this paper
• Fully unsupervised word translation from cross-lingual word embeddings especially for healthcare professionals

  2021cites this paper
• Exploring Cross-Lingual Transfer Learning with Unsupervised Machine Translation

  2021cites this paper
• Cross-Lingual BERT Contextual Embedding Space Mapping with Isotropic and Isometric Conditions

  2021cites this paper
• Multi-Granularity Contrasting for Cross-Lingual Pre-Training

  2021cites this paper
• Combining Static Word Embeddings and Contextual Representations for Bilingual Lexicon Induction

  2021cites this paper
• AdvPicker: Effectively Leveraging Unlabeled Data via Adversarial Discriminator for Cross-Lingual NER

  2021cites this paper
• Exploiting Language Relatedness for Low Web-Resource Language Model Adaptation: An Indic Languages Study

  2021cites this paper
• Does Robustness Improve Fairness? Approaching Fairness with Word Substitution Robustness Methods for Text Classification

  2021cites this paper
• Improving Zero-Shot Cross-lingual Transfer for Multilingual Question Answering over Knowledge Graph

  2021cites this paper
• An exploration of semi-supervised and language-adversarial transfer learning using hybrid acoustic model for hindi speech recognition

  2021cites this paper
• Word Embedding Transformation for Robust Unsupervised Bilingual Lexicon Induction

  2021cites this paper
• Bilingual alignment transfers to multilingual alignment for unsupervised parallel text mining

  2021cites this paper
• Filtered Inner Product Projection for Crosslingual Embedding Alignment

  2021influential citation
• A Survey on Low-Resource Neural Machine Translation

  2021cites this paper
• Cross-lingual Transferring of Pre-trained Contextualized Language Models

  2021cites this paper
• Bilingual Terminology Extraction from Non-Parallel E-Commerce Corpora

  2021cites this paper
• Adversarial training with Wasserstein distance for learning cross-lingual word embeddings

  2021influential citation
• Transferring Knowledge Distillation for Multilingual Social Event Detection

  2021cites this paper
• Towards mining bilingual lexicons and parallel phrases from large-scale monolingual corpora

  2021cites this paper
• A word embedding-based approach to cross-lingual topic modeling

  2021cites this paper
• Bilingual Lexicon Induction via Unsupervised Bitext Construction and Word Alignment

  2021cites this paper
• Commonsense Knowledge Augmentation for Low-Resource Languages via Adversarial Learning

  2021cites this paper
• Do not neglect related languages: The case of low-resource Occitan cross-lingual word embeddings

  2021cites this paper
• El Volumen Louder Por Favor: Code-switching in Task-oriented Semantic Parsing

  2021cites this paper
• Efficient bilingual lexicon extraction from comparable corpora based on formal concepts analysis

  2021influential citation
• Empirical Regularization for Synthetic Sentence Pairs in Unsupervised Neural Machine Translation

  2021cites this paper
• Filtered Inner Product Projection for Multilingual Embedding Alignment

  2020cites this paper
• Cross-lingual Sentiment Analysis via AAE and BiGRU

  2020cites this paper
• Attend, Translate and Summarize: An Efficient Method for Neural Cross-Lingual Summarization

  2020cites this paper