natural-language-processing-10

Cross-Lingual Word Embeddings

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in cross-lingual-word-embeddings-10

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find cross-lingual-word-embeddings-10 models and implementations

artetxem/vecmap

2 papers 639

Datasets

No datasets available.

Subtasks

No subtasks available.

Most implemented papers

Word Translation Without Parallel Data

Marc'Aurelio Ranzato, Herv'e J'egou, Alexis Conneau, Guillaume Lample, Ludovic Denoyer•Tue Oct 10 2017

It is shown that a bilingual dictionary can be built between two languages without using any parallel corpora, by aligning monolingual word embedding spaces in an unsupervised way.

1734

Content

0

Paper Graph

A robust self-learning method for fully unsupervised cross-lingual mappings of word embeddings

Eneko Agirre, Mikel Artetxe, Gorka Labaka•Tue May 15 2018

This work proposes an alternative approach based on a fully unsupervised initialization that explicitly exploits the structural similarity of the embeddings, and a robust self-learning algorithm that iteratively improves this solution.

610 0

Paper Graph

Lost in Evaluation: Misleading Benchmarks for Bilingual Dictionary Induction

Anders Søgaard, Yova Kementchedjhieva, Mareike Hartmann•Wed Sep 11 2019

It is suggested that future research either avoids drawing conclusions from quantitative results on this BDI dataset, or accompanies such evaluation with rigorous error analysis.

37 0

Paper Graph

A Pilot Study for Chinese SQL Semantic Parsing

Yu Shi, Qingkai Min, Yue Zhang•Sat Sep 28 2019

A Spider dataset for Chinese is built, showing that word-based semantic parser is subject to segmentation errors and cross-lingual word embeddings are useful for text-to-SQL.

72 0

Paper Graph

Robust Cross-lingual Embeddings from Parallel Sentences

Martin Jaggi, Robert West, A. Sabet, Prakhar Gupta, Jean-Baptiste Cordonnier•Tue Sep 24 2019

This work proposes a bilingual extension of the CBOW method which leverages sentence-aligned corpora to obtain robust cross-lingual word and sentence representations and significantly improves cross-lingsual sentence retrieval performance over all other approaches while maintaining parity with the current state-of-the-art methods on word-translation.

15 0

Paper Graph

Baselines and Test Data for Cross-Lingual Inference

Zeljko Agic, Natalie Schluter•Mon Apr 17 2017

This paper proposes to advance the research in SNLI-style natural language inference toward multilingual evaluation and provides test data for four major languages: Arabic, French, Spanish, and Russian, based on cross-lingual word embeddings and machine translation.

28 0

Paper Graph

Model Transfer for Tagging Low-resource Languages using a Bilingual Dictionary

Trevor Cohn, Meng Fang•Sun Apr 30 2017

This work proposes a novel neural network model for joint training from both sources of data based on cross-lingual word embeddings, and shows substantial empirical improvements over baseline techniques.

76 0

Paper Graph

Improving Cross-Lingual Word Embeddings by Meeting in the Middle

S. Schockaert, José Camacho-Collados, Luis Espinosa Anke, Yerai Doval•Sun Aug 26 2018

This work proposes to apply an additional transformation after the initial alignment step, which moves cross-lingual synonyms towards a middle point between them, and aims to obtain a better cross-lingsual integration of the vector spaces.

62 0

Paper Graph

How to (Properly) Evaluate Cross-Lingual Word Embeddings: On Strong Baselines, Comparative Analyses, and Some Misconceptions

Sebastian Ruder, Ivan Vulic, Goran Glavas, Robert Litschko•Thu Jan 31 2019

It is empirically demonstrate that the performance of CLE models largely depends on the task at hand and that optimizing CLE models for BLI may hurt downstream performance, and indicates the most robust supervised and unsupervised CLE models.

188 0

Paper Graph

Are Girls Neko or Shōjo? Cross-Lingual Alignment of Non-Isomorphic Embeddings with Iterative Normalization

S. Jegelka, Keyulu Xu, K. Kawarabayashi, Mozhi Zhang, Jordan L. Boyd-Graber•Mon Jun 03 2019

Iterative Normalization consistently improves word translation accuracy of three CLWE methods, with the largest improvement observed on English-Japanese (from 2% to 44% test accuracy).

63 0

Paper Graph

Adding a benchmark result helps the community track progress.