Prakhar Gupta

Edit profile

prakhar.gupta@epfl.ch +41 21 693 16 81

Citizenship: Indian

Google Scholar Link

https://scholar.google.ch/citations?user=wRJyHpIAAAAJ&hl=en&oi=ao

+41 21 693 16 81
EPFL > CDM > MTEI > STIP

Web site: Web site: https://www.epfl.ch/labs/iipp/

vCard
Administrative data

Fields of expertise

Machine Learning, Natural Language Processing and Optimization

Education

B.Tech.

Aerospace Engineering

Indian Institute of Technology Kanpur

2010-14

M.Tech.

Computer Science and Engineering

Indian Institute of Technology Bombay

2014-16

Publications

Infoscience publications

Unsupervised learning of sentence embeddings

Unsupervised learning of sentence embeddings using compositional n-gram features - Infoscience <script type="text/javascript" src="/js/jquery.min.js"></script> <script type="text/javascript" src="/js/tind.js?425ae572c71e1fce6a7cb4b88d683e2b"></script> login

Home > Unsupervised learning of sentence embeddings using compositional n-gram features

Information
Usage statistics
Files

Unsupervised learning of sentence embeddings using compositional n-gram features Pagliardini, Matteo ; Gupta, Prakhar ; Jaggi, Martin
Presented at: NAACL 2018 - Conference of the North American Chapter of the Association for Computational Linguistics Year:May 01 2018 Laboratories: MLO
Record appears in:Scientific production and competences > I&C - School of Computer and Communication Sciences > IINFCOM > MLO - Machine Learning and Optimization Laboratory
Conference Papers
Work produced at EPFL

Fulltext: untitled - PDF;
Export as: BibTeX | MARC | MARCXML | DC | EndNote | NLM | RefWorks | RIS
View as: MARC | MARCXML | DC
Add to your basket:

Back to search Record created 2018-05-14, last modified 2019-08-12
Fulltext:

PDF
Rate this document:

Rate this document: 1 2 3 4 5 (Not yet reviewed)

Add to personal basket
Export as BibTeX, MARC, MARCXML, DC, EndNote, NLM, RefWorks

Learning Word Vectors for 157 Languages

Learning Word Vectors for 157 Languages - Infoscience <script type="text/javascript" src="/js/jquery.min.js"></script> <script type="text/javascript" src="/js/tind.js?425ae572c71e1fce6a7cb4b88d683e2b"></script> login

Home > Learning Word Vectors for 157 Languages

Information
Usage statistics
Files

Learning Word Vectors for 157 Languages Grave, Edouard ; Bojanowski, Piotr ; Gupta, Prakhar ; Joulin, Armand ; Mikolov, Tomas ; Grave, Edouard ; Bojanowski, Piotr ; Joulin, Armand ; Mikolov, Tomas Distributed word representations, or word vectors, have recently been applied to many tasks in natural language processing, leading to state-of-the-art performance. A key ingredient to the successful application of these representations is to train them on very large corpora, and use these pre-trained models in downstream tasks. In this paper, we describe how we trained such high quality word representations for 157 languages. We used two sources of data to train these models: the free online encyclopedia Wikipedia and data from the common crawl project. We also introduce three new word analogy datasets to evaluate these word vectors, for French, Hindi and Polish. Finally, we evaluate our pre-trained word vectors on 10 languages for which evaluation datasets exists, showing very strong performance compared to previous models.
Presented at: Language Resources and Evaluation Conference, Miyazaki, Japan, May 7-12, 2018 Year:Feb 19 2018 Laboratories: MLO
Record appears in:Scientific production and competences > I&C - School of Computer and Communication Sciences > IINFCOM > MLO - Machine Learning and Optimization Laboratory
Work outside EPFL
Conference Papers

Fulltext: 1802.06893 - PDF;
Export as: BibTeX | MARC | MARCXML | DC | EndNote | NLM | RefWorks | RIS
View as: MARC | MARCXML | DC
Add to your basket:

Back to search Record created 2018-03-05, last modified 2019-08-12
Fulltext: