embeddings with almost
play

embeddings with (almost) no bilingual data Mik ikel l Art - PowerPoint PPT Presentation

Aug 19, 2023 •277 likes •1.63k views

Learning bilingual word embeddings with (almost) no bilingual data Mik ikel l Art rtetxe, Gorka Labaka, Eneko Agirre IXA NLP group University of the Basque Country (UPV/EHU) Who cares? Who cares? word embeddings are useful! Who

  1. Experiments • Dataset by Dinu et al. (2015) extended to German and Finnish ⇒ Monolingual embeddings (CBOW + negative sampling) ⇒ Seed dictionary: 5,000 word pairs / 25 word pairs / numerals Eng English-Italian Eng English-German Eng English-Finnish 5,00 ,000 25 25 num num. 5,00 ,000 25 25 num num. 5,00 ,000 25 25 num num.

  2. Experiments • Dataset by Dinu et al. (2015) extended to German and Finnish ⇒ Monolingual embeddings (CBOW + negative sampling) ⇒ Seed dictionary: 5,000 word pairs / 25 word pairs / numerals ⇒ Test dictionary: 1,500 word pairs Eng English-Italian Eng English-German Eng English-Finnish 5,00 ,000 25 25 num num. 5,00 ,000 25 25 num num. 5,00 ,000 25 25 num num.

  3. Experiments • Dataset by Dinu et al. (2015) extended to German and Finnish ⇒ Monolingual embeddings (CBOW + negative sampling) ⇒ Seed dictionary: 5,000 word pairs / 25 word pairs / numerals ⇒ Test dictionary: 1,500 word pairs Eng English-Italian Eng English-German Eng English-Finnish 5,00 ,000 25 25 num. num 5,00 ,000 25 25 num num. 5,00 ,000 25 25 num num. wor ord translation inductio ion

  4. Experiments • Dataset by Dinu et al. (2015) extended to German and Finnish ⇒ Monolingual embeddings (CBOW + negative sampling) ⇒ Seed dictionary: 5,000 word pairs / 25 word pairs / numerals ⇒ Test dictionary: 1,500 word pairs Eng English-Italian Eng English-German Eng English-Finnish 5,00 ,000 25 25 num num. 5,00 ,000 25 25 num num. 5,00 ,000 25 25 num num. Mikolov et al. (2013a) Xing et al. (2015) Zhang et al. (2016) Artetxe et al. (2016) wor ord translation inductio ion

  5. Experiments • Dataset by Dinu et al. (2015) extended to German and Finnish ⇒ Monolingual embeddings (CBOW + negative sampling) ⇒ Seed dictionary: 5,000 word pairs / 25 word pairs / numerals ⇒ Test dictionary: 1,500 word pairs Eng English-Italian Eng English-German Eng English-Finnish 5,00 ,000 25 25 num num. 5,00 ,000 25 25 num num. 5,00 ,000 25 25 num. num Mikolov et al. (2013a) Xing et al. (2015) Zhang et al. (2016) Artetxe et al. (2016) Our method wor ord translation inductio ion

  6. Experiments • Dataset by Dinu et al. (2015) extended to German and Finnish ⇒ Monolingual embeddings (CBOW + negative sampling) ⇒ Seed dictionary: 5,000 word pairs / 25 word pairs / numerals ⇒ Test dictionary: 1,500 word pairs Eng English-Italian Eng English-German English-Finnish Eng 5,00 ,000 25 25 num num. 5,00 ,000 25 25 num. num 5,00 ,000 25 25 num num. Mikolov et al. (2013a) 34.93% 0.00% 0.00% 35.00% 0.00% 0.07% 25.91% 0.00% 0.00% Xing et al. (2015) 36.87% 0.00% 0.13% 41.27% 0.07% 0.53% 28.23% 0.07% 0.56% Zhang et al. (2016) 36.73% 0.07% 0.27% 40.80% 0.13% 0.87% 28.16% 0.14% 0.42% Artetxe et al. (2016) 39.27% 0.07% 0.40% 41.87 .87% 0.13% 0.73% 30.62 .62% 0.21% 0.77% Our method 39.67 .67% 37.27 .27% 39.40 .40% 40.87% 39.60 .60% 40.27 .27% 28.72% 28.16 .16% 26.47 .47% wor ord translation inductio ion

  7. Experiments • Dataset by Dinu et al. (2015) extended to German and Finnish ⇒ Monolingual embeddings (CBOW + negative sampling) ⇒ Seed dictionary: 5,000 word pairs / 25 word pairs / numerals ⇒ Test dictionary: 1,500 word pairs Eng English-Italian Eng English-German English-Finnish Eng 5,00 ,000 25 25 num num. 5,00 ,000 25 25 num. num 5,00 ,000 25 25 num num. Mikolov et al. (2013a) 34.93% 0.00% 0.00% 35.00% 0.00% 0.07% 25.91% 0.00% 0.00% Xing et al. (2015) 36.87% 0.00% 0.13% 41.27% 0.07% 0.53% 28.23% 0.07% 0.56% Zhang et al. (2016) 36.73% 0.07% 0.27% 40.80% 0.13% 0.87% 28.16% 0.14% 0.42% Artetxe et al. (2016) 39.27% 0.07% 0.40% 41.87 .87% 0.13% 0.73% 30.62 .62% 0.21% 0.77% Our method 39.67 .67% 37.27 .27% 39.40 .40% 40.87% 39.60 .60% 40.27 .27% 28.72% 28.16 .16% 26.47 .47% wor ord translation inductio ion

  8. Experiments • Dataset by Dinu et al. (2015) extended to German and Finnish ⇒ Monolingual embeddings (CBOW + negative sampling) ⇒ Seed dictionary: 5,000 word pairs / 25 word pairs / numerals ⇒ Test dictionary: 1,500 word pairs Eng English-Italian Eng English-German English-Finnish Eng 5,00 ,000 25 25 num num. 5,00 ,000 25 25 num. num 5,00 ,000 25 25 num num. Mikolov et al. (2013a) 34.93% 0.00% 0.00% 35.00% 0.00% 0.07% 25.91% 0.00% 0.00% Xing et al. (2015) 36.87% 0.00% 0.13% 41.27% 0.07% 0.53% 28.23% 0.07% 0.56% Zhang et al. (2016) 36.73% 0.07% 0.27% 40.80% 0.13% 0.87% 28.16% 0.14% 0.42% Artetxe et al. (2016) 39.27% 0.07% 0.40% 41.87 .87% 0.13% 0.73% 30.62 .62% 0.21% 0.77% Our method 39.67 .67% 37.27 .27% 39.40 .40% 40.87% 39.60 .60% 40.27 .27% 28.72% 28.16 .16% 26.47 .47% wor ord translation inductio ion

  9. Experiments • Dataset by Dinu et al. (2015) extended to German and Finnish ⇒ Monolingual embeddings (CBOW + negative sampling) ⇒ Seed dictionary: 5,000 word pairs / 25 word pairs / numerals ⇒ Test dictionary: 1,500 word pairs Eng English-Italian Eng English-German English-Finnish Eng 5,00 ,000 25 25 num num. 5,00 ,000 25 25 num. num 5,00 ,000 25 25 num num. Mikolov et al. (2013a) 34.93% 0.00% 0.00% 35.00% 0.00% 0.07% 25.91% 0.00% 0.00% Xing et al. (2015) 36.87% 0.00% 0.13% 41.27% 0.07% 0.53% 28.23% 0.07% 0.56% Zhang et al. (2016) 36.73% 0.07% 0.27% 40.80% 0.13% 0.87% 28.16% 0.14% 0.42% Artetxe et al. (2016) 39.27% 0.07% 0.40% 41.87 .87% 0.13% 0.73% 30.62 .62% 0.21% 0.77% Our method 39.67 .67% 37.27 .27% 39.40 .40% 40.87% 39.60 .60% 40.27 .27% 28.72% 28.16 .16% 26.47 .47% wor ord translation inductio ion

  10. Experiments • Dataset by Dinu et al. (2015) extended to German and Finnish ⇒ Monolingual embeddings (CBOW + negative sampling) ⇒ Seed dictionary: 5,000 word pairs / 25 word pairs / numerals ⇒ Test dictionary: 1,500 word pairs Eng English-Italian Eng English-German English-Finnish Eng 5,00 ,000 25 25 num num. 5,00 ,000 25 25 num. num 5,00 ,000 25 25 num num. Mikolov et al. (2013a) 34.93% 0.00% 0.00% 35.00% 0.00% 0.07% 25.91% 0.00% 0.00% Xing et al. (2015) 36.87% 0.00% 0.13% 41.27% 0.07% 0.53% 28.23% 0.07% 0.56% Zhang et al. (2016) 36.73% 0.07% 0.27% 40.80% 0.13% 0.87% 28.16% 0.14% 0.42% Artetxe et al. (2016) 39.27% 0.07% 0.40% 41.87 .87% 0.13% 0.73% 30.62 .62% 0.21% 0.77% Our method 39.67 .67% 37.27 .27% 39.40 .40% 40.87% 39.60 .60% 40.27 .27% 28.72% 28.16 .16% 26.47 .47% wor ord translation inductio ion

  11. Experiments • Dataset by Dinu et al. (2015) extended to German and Finnish ⇒ Monolingual embeddings (CBOW + negative sampling) ⇒ Seed dictionary: 5,000 word pairs / 25 word pairs / numerals ⇒ Test dictionary: 1,500 word pairs Eng English-Italian 5,00 ,000 25 25 num num. Mikolov et al. (2013a) 34.93% 0.00% 0.00% Xing et al. (2015) 36.87% 0.00% 0.13% Zhang et al. (2016) 36.73% 0.07% 0.27% Artetxe et al. (2016) 39.27% 0.07% 0.40% Our method 39.67 .67% 37.27 .27% 39.40 .40% wor ord translation inductio ion

  12. Experiments • Dataset by Dinu et al. (2015) extended to German and Finnish ⇒ Monolingual embeddings (CBOW + negative sampling) ⇒ Seed dictionary: 5,000 word pairs / 25 word pairs / numerals

  13. Experiments • Dataset by Dinu et al. (2015) extended to German and Finnish ⇒ Monolingual embeddings (CBOW + negative sampling) ⇒ Seed dictionary: 5,000 word pairs / 25 word pairs / numerals cros ossli lingual wor ord si simil ilarity

  14. Experiments • Dataset by Dinu et al. (2015) extended to German and Finnish ⇒ Monolingual embeddings (CBOW + negative sampling) ⇒ Seed dictionary: 5,000 word pairs / 25 word pairs / numerals EN EN-IT IT EN EN-DE DE WS WS RG RG WS WS cros ossli lingual wor ord si simil ilarity

  15. Experiments • Dataset by Dinu et al. (2015) extended to German and Finnish ⇒ Monolingual embeddings (CBOW + negative sampling) ⇒ Seed dictionary: 5,000 word pairs / 25 word pairs / numerals EN EN-IT IT EN EN-DE DE Bi Bi. . da data WS WS RG RG WS WS cros ossli lingual wor ord si simil ilarity

  16. Experiments • Dataset by Dinu et al. (2015) extended to German and Finnish ⇒ Monolingual embeddings (CBOW + negative sampling) ⇒ Seed dictionary: 5,000 word pairs / 25 word pairs / numerals EN EN-IT IT EN EN-DE DE Bi Bi. . da data WS WS RG RG WS WS Luong et al. (2015) Europarl cros ossli lingual wor ord si simil ilarity

  17. Experiments • Dataset by Dinu et al. (2015) extended to German and Finnish ⇒ Monolingual embeddings (CBOW + negative sampling) ⇒ Seed dictionary: 5,000 word pairs / 25 word pairs / numerals EN EN-IT IT EN EN-DE DE Bi Bi. . da data WS WS RG RG WS WS Luong et al. (2015) Europarl Mikolov et al. (2013a) 5k dict Xing et al. (2015) 5k dict Zhang et al. (2016) 5k dict Artetxe et al. (2016) 5k dict cros ossli lingual wor ord si simil ilarity

  18. Experiments • Dataset by Dinu et al. (2015) extended to German and Finnish ⇒ Monolingual embeddings (CBOW + negative sampling) ⇒ Seed dictionary: 5,000 word pairs / 25 word pairs / numerals EN EN-IT IT EN EN-DE DE Bi Bi. . da data WS WS RG RG WS WS Luong et al. (2015) Europarl Mikolov et al. (2013a) 5k dict Xing et al. (2015) 5k dict Zhang et al. (2016) 5k dict Artetxe et al. (2016) 5k dict 5k dict Our method 25 dict num. cros ossli lingual wor ord si simil ilarity

  19. Experiments • Dataset by Dinu et al. (2015) extended to German and Finnish ⇒ Monolingual embeddings (CBOW + negative sampling) ⇒ Seed dictionary: 5,000 word pairs / 25 word pairs / numerals EN EN-IT IT EN EN-DE DE Bi Bi. . da data WS WS RG RG WS WS Luong et al. (2015) Europarl 33.1% 33.5% 35.6% Mikolov et al. (2013a) 5k dict 62.7% 64.3% 52.8% Xing et al. (2015) 5k dict 61.4% 70.0% 59.5% Zhang et al. (2016) 5k dict 61.6% 70.4% 59.6% Artetxe et al. (2016) 5k dict 61.7% 71.6% 59.7% 5k dict 62.4% 74.2% 61.6% .6% Our method 25 dict 62.6% 74.9% .9% 61.2% num. 62.8% .8% 73.9% 60.4% cros ossli lingual wor ord si simil ilarity

  20. Experiments • Dataset by Dinu et al. (2015) extended to German and Finnish ⇒ Monolingual embeddings (CBOW + negative sampling) ⇒ Seed dictionary: 5,000 word pairs / 25 word pairs / numerals EN EN-IT IT EN EN-DE DE Bi Bi. . da data WS WS RG RG WS WS Luong et al. (2015) Europarl 33.1% 33.5% 35.6% Mikolov et al. (2013a) 5k dict 62.7% 64.3% 52.8% Xing et al. (2015) 5k dict 61.4% 70.0% 59.5% Zhang et al. (2016) 5k dict 61.6% 70.4% 59.6% Artetxe et al. (2016) 5k dict 61.7% 71.6% 59.7% 5k dict 62.4% 74.2% 61.6% .6% Our method 25 dict 62.6% 74.9% .9% 61.2% num. 62.8% .8% 73.9% 60.4% cros ossli lingual wor ord si simil ilarity

  21. Experiments • Dataset by Dinu et al. (2015) extended to German and Finnish ⇒ Monolingual embeddings (CBOW + negative sampling) ⇒ Seed dictionary: 5,000 word pairs / 25 word pairs / numerals EN EN-IT IT EN EN-DE DE Bi Bi. . da data WS WS RG RG WS WS Luong et al. (2015) Europarl 33.1% 33.5% 35.6% Mikolov et al. (2013a) 5k dict 62.7% 64.3% 52.8% Xing et al. (2015) 5k dict 61.4% 70.0% 59.5% Zhang et al. (2016) 5k dict 61.6% 70.4% 59.6% Artetxe et al. (2016) 5k dict 61.7% 71.6% 59.7% 5k dict 62.4% 74.2% 61.6% .6% Our method 25 dict 62.6% 74.9% .9% 61.2% num. 62.8% .8% 73.9% 60.4% cros ossli lingual wor ord si simil ilarity

  22. Why does it work?

  23. Why does it work? Monolingual embeddings Dictionary Mapping Dictionary

  24. Why does it work? Monolingual embeddings small Dictionary Mapping Dictionary

  25. Why does it work? Monolingual embeddings small la large Dictionary Mapping Dictionary

  26. Why does it work? Monolingual embeddings small la large Dictionary Mapping Dictionary no o err rror

  27. Why does it work? Monolingual embeddings small la large Dictionary Mapping Dictionary no o err rror er errors

  28. Why does it work? Monolingual embeddings small la large Dictionary Mapping Dictionary no o err rror er errors Mapping Dictionary

  29. Why does it work? Monolingual embeddings small la large Dictionary Mapping Dictionary no o err rror er errors better? Mapping Dictionary

  30. Why does it work? Monolingual embeddings small large la Dictionary Mapping Dictionary no o err rror er errors better? Mapping Dictionary worse?

  31. Why does it work? Monolingual embeddings small la large Dictionary Mapping Dictionary no o err rror er errors better? Mapping Dictionary worse? Mapping Dictionary

  32. Why does it work? Monolingual embeddings small large la Dictionary Mapping Dictionary no o err rror er errors better? Mapping Dictionary worse? even en better? Mapping Dictionary

  33. Why does it work? Monolingual embeddings small large la Dictionary Mapping Dictionary no o err rror er errors better? Mapping Dictionary worse? even en better? Mapping Dictionary even en worse?

  34. Why does it work? 𝑌𝑋 𝑎

  35. Why does it work? 𝑌𝑋 𝑎 𝑋 ∗ = arg max s.t. 𝑋𝑋 𝑈 = 𝑋 𝑈 𝑋 = 𝐽 Implicit objective: ෍ max 𝑌 𝑗∗ 𝑋 ∙ 𝑎 𝑘∗ 𝑘 𝑋 𝑗

  36. Why does it work? 𝑌𝑋 𝑎 𝑋 ∗ = arg max s.t. 𝑋𝑋 𝑈 = 𝑋 𝑈 𝑋 = 𝐽 Implicit objective: ෍ max 𝑌 𝑗∗ 𝑋 ∙ 𝑎 𝑘∗ 𝑘 𝑋 𝑗 Independent from seed dictionary!

  37. Why does it work? 𝑌𝑋 𝑎 𝑋 ∗ = arg max s.t. 𝑋𝑋 𝑈 = 𝑋 𝑈 𝑋 = 𝐽 Implicit objective: ෍ max 𝑌 𝑗∗ 𝑋 ∙ 𝑎 𝑘∗ 𝑘 𝑋 𝑗

  38. Why does it work? 𝑌𝑋 𝑎 𝑋 ∗ = arg max s.t. 𝑋𝑋 𝑈 = 𝑋 𝑈 𝑋 = 𝐽 Implicit objective: ෍ max 𝑌 𝑗∗ 𝑋 ∙ 𝑎 𝑘∗ 𝑘 𝑋 𝑗

  39. Why does it work? 𝑌𝑋 𝑎 𝑋 ∗ = arg max s.t. 𝑋𝑋 𝑈 = 𝑋 𝑈 𝑋 = 𝐽 Implicit objective: ෍ max 𝑌 𝑗∗ 𝑋 ∙ 𝑎 𝑘∗ 𝑘 𝑋 𝑗

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend

Word Embeddings Natural Language Processing VU (706.230) - Andi Rexha 02/04/2020 Word Embeddings

Word Embeddings Natural Language Processing VU (706.230) - Andi Rexha 02/04/2020 Word Embeddings

Word Embeddings Natural Language Processing VU (706.230) - Andi Rexha 02/04/2020 Word Embeddings Agenda Traditional NLP Word Embeddings-1 Word Embeddings-2 Text preprocessing Topic Modeling ELMo Bag-of-words model Neural

900 views • 64 slides
Word Embeddings CS 6956: Deep Learning for NLP Overview Representing meaning Word

Word Embeddings CS 6956: Deep Learning for NLP Overview Representing meaning Word

Word Embeddings CS 6956: Deep Learning for NLP Overview Representing meaning Word embeddings: Early work Word embeddings via language models Word2vec and Glove Evaluating embeddings Design choices and open questions 1

422 views • 17 slides
Word Embeddings CS 6956: Deep Learning for NLP Overview Representing meaning Word

Word Embeddings CS 6956: Deep Learning for NLP Overview Representing meaning Word

Word Embeddings CS 6956: Deep Learning for NLP Overview Representing meaning Word embeddings: Early work Word embeddings via language models Word2vec and Glove Evaluating embeddings Design choices and open questions 1

2k views • 24 slides
Word Embeddings CS 6956: Deep Learning for NLP Overview Representing meaning Word

Word Embeddings CS 6956: Deep Learning for NLP Overview Representing meaning Word

Word Embeddings CS 6956: Deep Learning for NLP Overview Representing meaning Word embeddings: Early work Word embeddings via language models Word2vec and Glove Evaluating embeddings Design choices and open questions 1

828 views • 15 slides
Word Embeddings CS 6956: Deep Learning for NLP Overview Representing meaning Word

Word Embeddings CS 6956: Deep Learning for NLP Overview Representing meaning Word

Word Embeddings CS 6956: Deep Learning for NLP Overview Representing meaning Word embeddings: Early work Word embeddings via language models Word2vec and Glove Evaluating embeddings Design choices and open questions 1

1.25k views • 75 slides
Word embeddings Rappel Embeddings ( pas Word Embeddings ) Est une lookup table Formalisme:

Word embeddings Rappel Embeddings ( pas Word Embeddings ) Est une lookup table Formalisme:

Word embeddings Rappel Embeddings ( pas Word Embeddings ) Est une lookup table Formalisme: Index dun mot: w i Table dembeddings (lookup matrix): V Embedding: e i e i = V( w i ) Reprsentation dun mot

780 views • 47 slides
Mixed membership word embeddings: Corpus-specific embeddings without big data James Foulds

Mixed membership word embeddings: Corpus-specific embeddings without big data James Foulds

Mixed membership word embeddings: Corpus-specific embeddings without big data James Foulds University of California, San Diego Southern California Machine Learning Symposium, Caltech, 11/18/2018 Word Embeddings Language models which learn

537 views • 32 slides
What is best for spoken langage understanding: small but task-dependent embeddings or huge but

What is best for spoken langage understanding: small but task-dependent embeddings or huge but

What is best for spoken langage understanding: small but task-dependent embeddings or huge but out-of-domain embeddings Sahar Ghannay, Antoine Neuraz, Sophie Rosset 1 Goal Focus on semantic evaluation of common word embeddings

360 views • 16 slides
Subspace Embeddings and p -Regression Using Exponential Random Variables David P. Woodruff

Subspace Embeddings and p -Regression Using Exponential Random Variables David P. Woodruff

Subspace Embeddings and p -Regression Using Exponential Random Variables David P. Woodruff and Qin Zhang IBM Research Almaden COLT13, June 12, 2013 1-1 Subspace embeddings Subspace embeddings: A distribution over linear maps : R n

810 views • 44 slides
Embeddings @ Twitter Making ML easy with Embeddings !!! Sept 2018 Agenda 1 Team 2 Whats an

Embeddings @ Twitter Making ML easy with Embeddings !!! Sept 2018 Agenda 1 Team 2 Whats an

Embeddings @ Twitter Making ML easy with Embeddings !!! Sept 2018 Agenda 1 Team 2 Whats an Embedding ? 3 Why Embeddings ? 4 Embeddings Pipeline 5 Whats Next Agenda 1 Team 2 Whats an Embedding ? 3 Why Embeddings ? 4

732 views • 40 slides
Word Embeddings Revisited: Contextual Embeddings CS 6956: Deep Learning for NLP Overview

Word Embeddings Revisited: Contextual Embeddings CS 6956: Deep Learning for NLP Overview

Word Embeddings Revisited: Contextual Embeddings CS 6956: Deep Learning for NLP Overview Word types and tokens Training contextual embeddings Embeddings from Language Models (ELMo) 1 Overview Word types and tokens Training

670 views • 40 slides
Z 2 -embeddings and Tournaments Radoslav Fulek , Jan Kyn cl Z 2 -embeddings and Tournaments

Z 2 -embeddings and Tournaments Radoslav Fulek , Jan Kyn cl Z 2 -embeddings and Tournaments

Z 2 -embeddings and Tournaments Radoslav Fulek , Jan Kyn cl Z 2 -embeddings and Tournaments Radoslav Fulek , Jan Kyn cl June 12, 2018 Drawings of Graphs Drawings of Graphs G = ( V, E ) is a simple graph . The set of vertices V is finite

596 views • 56 slides
CS 4803 / 7643: Deep Learning Guest Lecture: Embeddings and world2vec Feb. 18 th 2020 Ledell Wu

CS 4803 / 7643: Deep Learning Guest Lecture: Embeddings and world2vec Feb. 18 th 2020 Ledell Wu

CS 4803 / 7643: Deep Learning Guest Lecture: Embeddings and world2vec Feb. 18 th 2020 Ledell Wu Research Engineer, Facebook AI ledell@fb.com 1 Outline Word Embeddings word2vec Graph Embeddings Applications world2vec

769 views • 41 slides
Dense Word Embeddings CMSC 470 Marine Carpuat Slides credit: Jurasky & Martin How to

Dense Word Embeddings CMSC 470 Marine Carpuat Slides credit: Jurasky & Martin How to

Dense Word Embeddings CMSC 470 Marine Carpuat Slides credit: Jurasky & Martin How to generate vector embeddings? One approach: feedforward neural language models Training a neural language model just to get word embeddings is expensive!

569 views • 38 slides
Dense Word Embeddings CMSC 470 Marine Carpuat Slides credit: Jurasky & Martin How to

Dense Word Embeddings CMSC 470 Marine Carpuat Slides credit: Jurasky & Martin How to

Dense Word Embeddings CMSC 470 Marine Carpuat Slides credit: Jurasky & Martin How to generate vector embeddings? One approach: feedforward neural language models Training a neural language model just to get word embeddings is expensive!

537 views • 35 slides
Embeddings for KB and text representation, extraction and question answering. Jason Weston

Embeddings for KB and text representation, extraction and question answering. Jason Weston

Embeddings for multi-relational data Pros and cons of embedding models Embeddings for KB and text representation, extraction and question answering. Jason Weston & Antoine Bordes & Sumit Chopra Facebook AI Research External

595 views • 24 slides
THE PRESENTATION OF A PLANNED TRILINGUAL LOGISTICS TERMINOLOGY DICTIONARY FOR LEARNERS RENATA

THE PRESENTATION OF A PLANNED TRILINGUAL LOGISTICS TERMINOLOGY DICTIONARY FOR LEARNERS RENATA

Advanced Logistic Systems Vol. 6. No. 1. (2012) pp. 75-82 THE PRESENTATION OF A PLANNED TRILINGUAL LOGISTICS TERMINOLOGY DICTIONARY FOR LEARNERS RENATA KRISTON 1 Abstract: This study is based on a previous article, where I presented the main

228 views • 8 slides
Development The development of a national IBM Strategy Borut Eren Border Management and Visa

Development The development of a national IBM Strategy Borut Eren Border Management and Visa

RABAT PROCESS Euro-African Dialogue on Migration and Development The development of a national IBM Strategy Borut Eren Border Management and Visa Madrid, November 5-6, 2013 EU IBM Guidance and Standards Borut Eren

259 views • 14 slides
GAVI RISK POLICY, RISK MANAGEMENT & FIDUCIARY OVERSIGHT BOARD MEETING Seth Berkley, Judith

GAVI RISK POLICY, RISK MANAGEMENT & FIDUCIARY OVERSIGHT BOARD MEETING Seth Berkley, Judith

GAVI RISK POLICY, RISK MANAGEMENT & FIDUCIARY OVERSIGHT BOARD MEETING Seth Berkley, Judith Kallenberg 10-11 December 2014, Geneva www.gavi.org OVERVIEW 1. Evolving risk management at Gavi 2. New risk management framework 3. Risk

479 views • 10 slides
Management of Contaminated Soil Oakland December 2, 2017 Co-hosts: Greenaction for Health and

Management of Contaminated Soil Oakland December 2, 2017 Co-hosts: Greenaction for Health and

Community Dialogue on the Management of Contaminated Soil Oakland December 2, 2017 Co-hosts: Greenaction for Health and Environmental Justice & West Oakland Environmental Indicators Project Community Feedback from Meeting #1 and #2

376 views • 15 slides
ArtsSemNet : From Bilingual Dictionary To Bilingual Semantic Network Ivanka Atanassova

ArtsSemNet : From Bilingual Dictionary To Bilingual Semantic Network Ivanka Atanassova

ArtsSemNet : From Bilingual Dictionary To Bilingual Semantic Network Ivanka Atanassova University of Veliko Tarnovo St. Cyril and Methodius Svetlin Nakov Sofia University St. Kliment Ohridski Preslav Nakov University of

430 views • 16 slides
When Dictionary Learning Meets Classification Bufford, Teresa 1 Chen, Yuxin 2 Horning, Mitchell 3

When Dictionary Learning Meets Classification Bufford, Teresa 1 Chen, Yuxin 2 Horning, Mitchell 3

The Method Supervised Unsupervised - spectral Unsupervised - k-means Gaussian Noise Experiments Additional Material When Dictionary Learning Meets Classification Bufford, Teresa 1 Chen, Yuxin 2 Horning, Mitchell 3 Shee, Liberty 1 Mentor:

532 views • 34 slides
Logical Categories and Parts of Speech as Structuring Devices in Pollux Onomasticon CHS

Logical Categories and Parts of Speech as Structuring Devices in Pollux Onomasticon CHS

Logical Categories and . . . . . . . . . . . . . . . . . . . . . . . . Logical Categories and Parts of Speech as Structuring Devices in Pollux Onomasticon CHS Biannual Research Symposium Fall 2016 Stelios

608 views • 35 slides
Structural Differences Between Two Graphs through Hierarchies Daniel Archambault 1 1 GRAVITE,

Structural Differences Between Two Graphs through Hierarchies Daniel Archambault 1 1 GRAVITE,

Structural Differences Between Two Graphs through Hierarchies Daniel Archambault 1 1 GRAVITE, INRIA Bordeaux Sud-Ouest, France Daniel Archambault Graph Difference 1/ 24 Introduction The Wine Difference Problem Wikimedia Project, Creative

540 views • 24 slides

More recommend