A Geometric View on Bilingual Lexicon Extraction from Comparable Corpora

We present a geometric view on bilingual lexicon extraction from comparable corpora, which allows to re-interpret the methods proposed so far and identify unresolved problems. This motivates three new methods that aim at solving these problems. Empirical evaluation shows the strengths and weaknesses of these methods, as well as a significant gain in the accuracy of extracted lexicons.

• Publication year

  2004

• Venue

  Annual Meeting of the Association for Computational Linguistics

• Publication date

  2004-07-21

• Fields of study

  Mathematics, Linguistics, Computer Science

• Identifiers
  DOI 10.3115/1218955.1219022
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Unsupervised Learning by Probabilistic Latent Semantic Analysis

  2004influential reference
• Kernel independent component analysis

  2003cited by this paper
• Learning a Translation Lexicon from Monolingual Corpora

  2002cited by this paper
• Inferring a Semantic Representation of Text via Cross-Language Correlation Analysis

  2002cited by this paper
• An Approach Based on Multilingual Thesauri and Model Combination for Bilingual Lexicon Extraction

  2002influential reference
• A statistical word-level translation model for comparable corpora

  2000cited by this paper
• Identifying Translations of Compound Nouns Using Non-aligned Corpora

  1999cited by this paper
• Probabilistic Latent Semantic Analysis

  1999influential reference
• Textual similarities based on a distributional approach

  1999cited by this paper
• Learning the Similarity of Documents: An Information-Geometric Approach to Document Retrieval and Categorization

  1999influential reference
• A Statistical View on Bilingual Lexicon Extraction: From Parallel Corpora to Non-parallel Corpora

  1998cited by this paper
• Exploiting Generative Models in Discriminative Classifiers

  1998cited by this paper
• Extraction of Lexical Translations from Non-Aligned Corpora

  1996cited by this paper
• Identifying Word Translations in Non-Parallel Texts

  1995cited by this paper
• Explorations in automatic thesaurus discovery

  1994cited by this paper
• Deterministic Annealing Variant of the EM Algorithm

  1994cited by this paper
• Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper

  1977cited by this paper
• Statistical Discrimination of the Synonymy/Antonymy Relationship Between Words

  1967cited by this paper

• Enhancing isomorphism between word embedding spaces for distant languages bilingual lexicon induction

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

  2024cites this paper
• On Bilingual Lexicon Induction with Large Language Models

  2023cites this paper
• Improving Word Translation via Two-Stage Contrastive Learning

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

  2022cites this paper
• Improving Bilingual Lexicon Induction with Cross-Encoder Reranking

  2022cites this paper
• A Systematic Literature Review on Extraction of Parallel Corpora from Comparable Corpora

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

  2021cites this paper
• An Unsupervised Semantic Model for Arabic/French Terminology Extraction

  2021cites this paper
• Data Selection for Bilingual Lexicon Induction from Specialized Comparable Corpora

  2020cites this paper
• Discovering Bilingual Lexicons in Polyglot Word Embeddings

  2020cites this paper
• What matters more: The size of the corpora or their quality?

  2020cites this paper
• SPMM: A Soft Piecewise Mapping Model for Bilingual Lexicon Induction

  2019cites this paper
• Cross-Lingual Word Embeddings

  2019cites this paper
• IMAGE-BASED BILINGUAL LEXICON INDUCTION FOR LOW RESOURCE LANGUAGES

  2019cites this paper
• Leveraging Meta-Embeddings for Bilingual Lexicon Extraction from Specialized Comparable Corpora

  2018cites this paper
• Identifying Word Translations in Scientific Literature Based on Labeled Bilingual Topic Model and Co-occurrence Features

  2018cites this paper
• A deep learning approach to bilingual lexicon induction in the biomedical domain

  2018cites this paper
• Review of techniques for extraction of bilingual lexicon from comparable corpora

  2018cites this paper
• Measuring bilingual corpus comparability

  2018cites this paper
• Bilingual Word Embeddings for Bilingual Terminology Extraction from Specialized Comparable Corpora

  2017cites this paper
• A Survey of Cross-lingual Word Embedding Models

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

  2017influential citation
• Adversarial Training for Unsupervised Bilingual Lexicon Induction

  2017cites this paper
• Earth Mover’s Distance Minimization for Unsupervised Bilingual Lexicon Induction

  2017cites this paper
• Corpus-Based Translation Induction in Indian Languages Using Auxiliary Language Corpora from Wikipedia

  2017cites this paper
• Bilingual Lexicon Induction by Learning to Combine Word-Level and Character-Level Representations

  2017cites this paper
• Integrating Local and Global Data View for Bilingual Sense Correspondences

  2017cites this paper
• Is (President, 大統領) a Correct Sense Pair? - Linking and Creating Bilingual Sense Correspondences

  2017cites this paper
• Deep embodiment: grounding semantics in perceptual modalities

  2017cites this paper
• Multi-Modal Representations for Improved Bilingual Lexicon Learning

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

  2016cites this paper
• Exploiting unbalanced specialized comparable corpora for bilingual lexicon extraction†

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

  2016influential citation
• Extracting translations from comparable corpora for Cross-Language Information Retrieval using the language modeling framework

  2016cites this paper
• Improving Bilingual Terminology Extraction from Comparable Corpora via Multiple Word-Space Models

  2016cites this paper
• Agreement-based Learning of Parallel Lexicons and Phrases from Non-Parallel Corpora

  2016cites this paper
• Sparse Bilingual Word Representations for Cross-lingual Lexical Entailment

  2016cites this paper
• Building a multi-domain comparable corpus using a learning to rank method†

  2016cites this paper
• Efficient Data Selection for Bilingual Terminology Extraction from Comparable Corpora

  2016cites this paper
• Integrated Parallel Data Extraction from Comparable Corpora for Statistical Machine Translation

  2015cites this paper
• Multilingual Topic Models for Bilingual Dictionary Extraction

  2015cites this paper
• A Generative Model for Extracting Parallel Fragments from Comparable Documents

  2015cites this paper
• Visual Bilingual Lexicon Induction with Transferred ConvNet Features

  2015cites this paper
• Probabilistic topic modeling in multilingual settings: An overview of its methodology and applications

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

  2015cites this paper
• Parallel Sentence Extraction Based on Unsupervised Bilingual Lexicon Extraction from Comparable Corpora

  2015cites this paper
• Bilingual Distributed Word Representations from Document-Aligned Comparable Data

  2015cites this paper
• Evaluating a Pivot-Based Approach for Bilingual Lexicon Extraction

  2015cites this paper
• Revisiting comparable corpora in connected space

  2015influential citation
• Bilingual lexicon extraction for a distant language pair using a small parallel corpus

  2015cites this paper
• A Methodology for Bilingual Lexicon Extraction from Comparable Corpora

  2015cites this paper
• Translation Induction on Indian Language Corpora Using Translingual Themes from Other Languages

  2015cites this paper
• Merging Comparable Data Sources for the Discrimination of Similar Languages : The DSL Corpus Collection

  2014cites this paper
• Improving Bilingual Lexicon Extraction from Comparable Corpora Using Window-Based and Syntax-Based Models

  2014cites this paper
• Probabilistic Models of Cross-Lingual Semantic Similarity in Context Based on Latent Cross-Lingual Concepts Induced from Comparable Data

  2014cites this paper
• Extraction de lexiques bilingues à partir de corpus comparables spécialisés : étude du contexte lexical [Bilingual lexicon extraction from specialized comparable corpora: a study of lexical context]

  2014cites this paper
• (Enhancing Performance of Bilingual Lexicon Extraction through Refinement of Pivot-Context Vectors)

  2014cites this paper
• Unsupervised Algorithms for Cross-Lingual Text Analysis, Translation Mining, and Information Retrieval (Algoritmen voor ongesuperviseerde cross-linguale tekstanalyse, het identificeren van vertalingen en informatieontsluiting)

  2014influential citation
• La Traduction automatique statistique dans un contexte multimodal. (Statistical machine translation in a multimodal context)

  2014cites this paper
• Looking at Unbalanced Specialized Comparable Corpora for Bilingual Lexicon Extraction

  2014cites this paper
• Constitution de ressources linguistiques multilingues à partir de corpus de textes parallèles et comparables. (Using parallel and comparable corpora for multilingual linguistic resources extraction)

  2014influential citation
• Mesures de comparabilité pour la construction assistée de corpus comparables bilingues thématiques. (Comparability measures for the assisted construction of bilingual thematic comparable corpora)

  2014cites this paper
• Comparabilty of Corpora in Human and Machine Translation

  2014cites this paper
• Combining Lexical Context with Pseudo-alignment for Bilingual Lexicon Extraction from Comparable Corpora

  2014cites this paper
• Unsupervised Algorithms for Cross-Lingual Text Analysis, Translation Mining, and Information Retrieval

  2014influential citation
• Towards a Generic Approach for Bilingual Lexicon Extraction from Comparable Corpora

  2013cites this paper
• Using WordNet and Semantic Similarity for Bilingual Terminology Mining from Comparable Corpora

  2013influential citation
• Topic Models + Word Alignment = A Flexible Framework for Extracting Bilingual Dictionary from Comparable Corpus

  2013cites this paper
• Context Vector Disambiguation for Bilingual Lexicon Extraction from Comparable Corpora

  2013cites this paper
• Building Specialized Bilingual Lexicons Using Word Sense Disambiguation

  2013cites this paper
• Bilingual Lexicon Extraction via Pivot Language and Word Alignment Tool

  2013cites this paper
• A Study on Bootstrapping Bilingual Vector Spaces from Non-Parallel Data (and Nothing Else)

  2013cites this paper
• Cross-language information retrieval models based on latent topic models trained with document-aligned comparable corpora

  2013cites this paper
• Cross-Lingual Semantic Similarity of Words as the Similarity of Their Semantic Word Responses

  2013cites this paper
• Multimodal Comparable Corpora as Resources for Extracting Parallel Data: Parallel Phrases Extraction

  2013cites this paper
• Bilingual Lexicon Extraction from Comparable Corpora by Combining Contextual Representations (Extraction de lexiques bilingues à partir de corpus comparables par combinaison de représentations contextuelles) [in French]

  2013cites this paper
• Veille épidémiologique multilingue : une approche parcimonieuse au grain caractèrefondée sur le genre textuel. (Multilingual epidemic surveillance : a parsimonious caracter-based approach)

  2013cites this paper
• (Utilisation de la similarité sémantique pour l’extraction de lexiques bilingues à partir de corpus comparables) [in French]

  2013cites this paper
• A Language Modeling Approach for Extracting Translation Knowledge from Comparable Corpora

  2013cites this paper
• Overviewing Important Aspects of the Last Twenty Years of Research in Comparable Corpora

  2013cites this paper
• Exploiting Comparable Corpora for Lexicon Extraction: Measuring and Improving Corpus Quality

  2013cites this paper
• Extracting Translation Pairs from Comparable Corpora through Graph-based Label Propagation

  2013cites this paper
• Extracting Parallel Fragments from Comparable Documents Using a Feature-Based Method

  2013cites this paper
• The Place of Comparable Corpora in Providing Terminological Reference Information to Online Translators: A Strategic Framework

  2013cites this paper
• Exploiting Comparable Corpora

  2013cites this paper
• Compositionnalité et contextes issus de corpus comparables pour la traduction terminologique (Compositionality and Context for Bilingual Lexicon Extraction from Comparable Corpora) [in French]

  2012cites this paper
• METRICC: Harnessing comparable corpora for multilingual lexicon development

  2012cites this paper
• Searching for patterns in the transfer of multiword units: a corpus-based contrastive study on secondary term formation

  2012cites this paper
• MEASURING AND IMPROVING COMPARABLE CORPUS QUALITY

  2012cites this paper
• Adaptive Dictionary for Bilingual Lexicon Extraction from Comparable Corpora

  2012cites this paper
• QAlign: A New Method for Bilingual Lexicon Extraction from Comparable Corpora

  2012cites this paper
• Bifid: un alineador de corpus paralelo a nivel de documento, oración y vocabulario

  2012cites this paper
• Statistical Extraction and Comparison of Pivot Words for Bilingual Lexicon Extension

  2012cites this paper
• Minimally supervised techniques for bilingual lexicon extraction

  2012cites this paper
• ICA for Bilingual Lexicon Extraction from Comparable Corpora

  2012cites this paper
• Learning Constructions of Natural Language: Statistical Models and Evaluations

  2012cites this paper
• Efficient corpus selection for statistical machine translation

  2012cites this paper
• Detecting Highly Confident Word Translations from Comparable Corpora without Any Prior Knowledge

  2012cites this paper
• STATISTICAL MACHINE TRANSLATION WITHOUT PARALLEL DATA

  2012cites this paper