CoChat

Bilingual Word Representations with Monolingual Quality in Mind

Open access
Luong, Thang, Pham, Hieu, Manning, Christopher D. · 2015 · Proceedings of the 1st Workshop on Vector Space Modeling for Natural Language Processing

The DOI matches its Crossref record; 47 of the 50 references it cites were found in a registry or an index.

Abstract

Recent work in learning bilingual representations tend to tailor towards achieving good performance on bilingual tasks, most often the crosslingual document classification (CLDC) evaluation, but to the detriment of preserving clustering structures of word representations monolingually.In this work, we propose a joint model to learn word representations from scratch that utilizes both the context coocurrence information through the monolingual component and the meaning equivalent signals from the bilingual constraint.Specifically, we extend the recently popular skipgram model to learn high quality bilingual representations efficiently.Our learned embeddings achieve a new state-of-the-art accuracy of 80.3 for the German to English CLDC task and a highly competitive performance of 90.7 for the other classification direction.At the same time, our models outperform best embeddings from past bilingual representation work by a large margin in the monolingual word similarity evaluation. 1

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.3115/v1/w15-1521

Cites

47 of 47 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 Bilingual Skipgram Model - besides predicting within languages, the model also predicts cross-lingually based on the alignment information. Glosses for German text are: modern economy trading [finance center] .
Figure 1 Bilingual Skipgram Model - besides predicting within languages, the model also predicts cross-lingually based on the alignment information. Glosses for German text are: modern economy trading [finance center] .CC-BY · From the PDF
Image 2
CC-BY · From the PDF

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

  • Glove: Global Vectors for Word Representation

    Pennington, J., Socher, R., & Manning, C. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1162 · Cited by 34,071 · cited 1×

    “Past work such as (Pennington et al., 2014; Faruqui and Dyer, 2014) among many others, have demonstrated that higher word similarity scores can be achieved by simply increasing the vocabulary coverage, training corpus size, and the embedding di-mension.”
    BackgroundSelf-citation
  • Latent dirichlet allocation

    (2003) · Journal of Machine Learning Research · doi:10.5555/944919.944937 · Cited by 32,337

  • Efficient Estimation of Word Representations in Vector Space

    Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1301.3781 · Cited by 26,568 · cited 6×

    “Recently, Mikolov et al. (2013a) introduced the skipgram (SG) approach for learning solely word embeddings by reversing the prediction process, that is, to use the current word to infer its surrounding context, as opposed to using preceding contexts to predict subsequent words in traditional…”
    MethodInfluential
  • Distributed Representations of Words and Phrases and their Compositionality

    Mikolov, T., Sutskever, I., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1310.4546 · Cited by 24,533 · cited 6×

    “Recently, Mikolov et al. (2013a) introduced the skipgram (SG) approach for learning solely word embeddings by reversing the prediction process, that is, to use the current word to infer its surrounding context, as opposed to using preceding contexts to predict subsequent words in traditional…”
    MethodInfluential
  • Latent Dirichlet Allocation

    Blei, D. M., Ng, A. Y., & Jordan, M. I. (2002) · Advances in Neural Information Processing Systems 14 · doi:10.7551/mitpress/1120.003.0082 · Cited by 12,223

  • Learning Word Vectors for Sentiment Analysis

    Maas, A. L., Daly, R. E., Pham, P. T., Huang, D., Ng, A. Y., & Potts, C. (2011) · Cited by 6,960

  • Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank

    Socher, R., Perelygin, A., Wu, J., Chuang, J., Manning, C. D., Ng, A., & Potts, C. (2013) · Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d13-1170 · Cited by 6,878 · cited 1×

    “…word representations have been key to the recent success of many neural network models in tackling various NLP tasks such as tagging, chunking (Collobert et al., 2011), sentiment analysis (Maas et al., 2011; Socher et al., 2013b), and parsing (Socher et al., 2013a; Chen and Manning, 2014).”
    BackgroundSelf-citation
  • Recurrent neural network based language model

    Mikolov, T., Karafiát, M., Burget, L., Černocký, J., & Khudanpur, S. (2010) · Interspeech 2010 · doi:10.21437/interspeech.2010-343 · Cited by 5,390

  • A unified architecture for natural language processing: deep neural networks with multitask learning

    Collobert, R., & Weston, J. (2008) · Proceedings of the 25th international conference on Machine learning - ICML '08 · doi:10.1145/1390156.1390177 · Cited by 5,058 · cited 1×

    “Work in the later trend includes (Collobert and Weston, 2008; Huang et al., 2012; Luong et al., 2013).”
  • Natural Language Processing (almost) from Scratch

    Collobert, R., Weston, J., Bottou, L., Karlen, M., Kavukcuoglu, K., & Kuksa, P. P. (2011) · arXiv (Cornell University) · doi:10.48550/arxiv.1103.0398 · Cited by 4,962 · cited 1×

    “…word representations have been key to the recent success of many neural network models in tackling various NLP tasks such as tagging, chunking (Collobert et al., 2011), sentiment analysis (Maas et al., 2011; Socher et al., 2013b), and parsing (Socher et al., 2013a; Chen and Manning, 2014).”
    Background

Show all 47 references

Research works printed but not linked: 5

  1. S. T. Dumais, G. W. Furnas, T. K. Landauer, S. Deer- wester, and R. Harshman. 1988. Using latent se- mantic analysis to improve access to textual infor- mation. In CHI.
  2. Stephan Gouws, Yoshua Bengio, and Greg Corrado. 2014. Bilbowa: Fast bilingual distributed repre- sentations without word alignments. In NIPS Deep Learning Workshop.
  3. Michael Gutmann and Aapo Hyvärinen. 2012. Noise- contrastive estimation of unnormalized statistical models, with applications to natural image statistics. JMLR, 13:307-361.
  4. Karl Moritz Hermann and Phil Blunsom. 2014. Multi- lingual Models for Compositional Distributional Se- mantics. In ACL.
  5. Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg Cor- rado, and Jeffrey Dean. 2013c. Distributed repre- sentations of words and phrases and their composi- tionality. In NIPS.

Cited by

  • Pre-trained models for natural language processing: A survey

    Qiu, X., Sun, T., Xu, Y., Shao, Y., Dai, N., & Huang, X. (2020) · Science China Technological Sciences · doi:10.1007/s11431-020-1647-3 · Cited by 1,591

    “tions shared across languages plays an important role in many cross-lingual NLP tasks. Cross-Lingual Language Understanding (XLU) Most of the early works focus on learning multilingual word embedding [45, 123, 158], which represents text from multiple languages in a single semantic space. However, these methods usuall…”
    Background
  • Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond

    Artetxe, M., & Schwenk, H. (2019) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00288 · Cited by 791

    “Most of this research focuses on cross-lingual word embeddings (Ruder et al., 2017), which are commonly learned jointly from parallel corpora (Gouws et al., 2015; Luong et al., 2015).”
    Background
  • Unsupervised Neural Machine Translation

    Artetxe, M., Labaka, G., Agirre, E., & Cho, K. (2017) · arXiv · doi:10.48550/arxiv.1710.11041 · Cited by 632

    “Most methods for learning cross-lingual word embeddings rely on some bilingual signal at the document level, typically in the form of parallel corpora (Gouws et al., 2015; Luong et al., 2015a).”
    Method
  • A Survey of Cross-lingual Word Embedding Models

    Ruder, S., Vulić, I., & Søgaard, A. (2018) · Apollo (University of Cambridge) · doi:10.17863/cam.30462 · Cited by 510

  • Learning bilingual word embeddings with (almost) no bilingual data

    Artetxe, M., Labaka, G., & Agirre, E. (2017) · Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p17-1042 · Cited by 455

    “In addition to the baseline systems in Section 4.2, in the crosslingual similarity experiments we also tested the method by Luong et al. (2015), which is the state-of-the-art for bilingual word embeddings based on parallel corpora (Upadhyay et al., 2016) 6 .”
    BackgroundMethodInfluential

See all 315

Metadata

Authors
Luong, T., Pham, H., & Manning, C. D.
Affiliations
Stanford University (US)
Corresponding author
Manning, Christopher D.
Venue
Proceedings of the 1st Workshop on Vector Space Modeling for Natural Language Processing
Published
2015
Pages
151-159
OpenAlex
W2251765408
Cited by
315
References
50
Citations by year
2026: 2 · 2025: 4 · 2024: 8 · 2023: 14 · 2022: 18 · 2021: 31 · 2020: 57 · 2019: 57 · 2018: 55 · 2017: 36 · 2016: 31 · 2015: 2
FWCI
23.29
Type
conference paper
Language
en
Open access
Licence
cc-by
Locations
Workshop on Vector Space Modeling for Natural Language Processing (VSM-NLP) (publishedVersion, cc-by)
Funders
  • Bloomberg L.P.
  • Defense Advanced Research Projects Agency (HR0011-12-C-0015)
  • Advanced Research Projects Agency
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
  • Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
  • Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
Keywords
word embeddings, skip-gram model, word co-occurrence, German-English translation

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.