machine translation contd
play

Machine Translation Contd Prof. Sameer Singh CS 295: STATISTICAL - PowerPoint PPT Presentation

Oct 29, 2023 •33 likes •553 views

Machine Translation Contd Prof. Sameer Singh CS 295: STATISTICAL NLP WINTER 2017 March 7, 2017 Based on slides from Richard Socher, Chris Manning, Philipp Koehn, and everyone else they copied from. Upcoming Status report due tonight: March

  1. Machine Translation Contd Prof. Sameer Singh CS 295: STATISTICAL NLP WINTER 2017 March 7, 2017 Based on slides from Richard Socher, Chris Manning, Philipp Koehn, and everyone else they copied from.

  2. Upcoming… Status report due tonight: March 7, 2017 • Project Almost final report, only 5 pages • Paper summaries: March 14 • Summaries • Summary 2 graded Homework 4 is due on March 13 • Homework • Write-up, code, and data released. Lowest grade of the homeworks will be dropped • CS 295: STATISTICAL NLP (WINTER 2017) 2

  3. Outline Decoding Algorithms Syntax-Based MT Neural MT Models CS 295: STATISTICAL NLP (WINTER 2017) 3

  4. Outline Decoding Algorithms Syntax-Based MT Neural MT Models CS 295: STATISTICAL NLP (WINTER 2017) 4

  5. Phrase Decoding: Stacks CS 295: STATISTICAL NLP (WINTER 2017) 5

  6. Monotonic Decoding CS 295: STATISTICAL NLP (WINTER 2017) 6

  7. Monotonic Phrase Decoding CS 295: STATISTICAL NLP (WINTER 2017) 7

  8. Monotonic Phrase Decoding (Mary) CS 295: STATISTICAL NLP (WINTER 2017) 8

  9. Monotonic Phrase Decoding (Mary) (did not) CS 295: STATISTICAL NLP (WINTER 2017) 9

  10. Monotonic Phrase Decoding (Mary) (did not) (slap) CS 295: STATISTICAL NLP (WINTER 2017) 10

  11. Monotonic Phrase Decoding (Mary) (did not) (slap) (the) CS 295: STATISTICAL NLP (WINTER 2017) 11

  12. Monotonic Phrase Decoding (Mary) (did not) (slap) (the) (green witch) CS 295: STATISTICAL NLP (WINTER 2017) 12

  13. Non-Monotonic Decoding CS 295: STATISTICAL NLP (WINTER 2017) 13

  14. Non-Monotonic Decoding CS 295: STATISTICAL NLP (WINTER 2017) 14

  15. Non-Monotonic Decoding CS 295: STATISTICAL NLP (WINTER 2017) 15

  16. Non-Monotonic Decoding CS 295: STATISTICAL NLP (WINTER 2017) 16

  17. Non-Monotonic Decoding CS 295: STATISTICAL NLP (WINTER 2017) 17

  18. Non-Monotonic Decoding CS 295: STATISTICAL NLP (WINTER 2017) 18

  19. Non-Monotonic Decoding CS 295: STATISTICAL NLP (WINTER 2017) 19

  20. Comparing Partial Translations CS 295: STATISTICAL NLP (WINTER 2017) 20

  21. Hypothesis Recombination CS 295: STATISTICAL NLP (WINTER 2017) 21

  22. Hypothesis Recombination CS 295: STATISTICAL NLP (WINTER 2017) 22

  23. Multi-Stack Decoding function S TACK D ECODING (source sentence) initialize stacks from 0..n for i = 0 .. n-1 for h in k-best hypothesis from stack[ i ] for h’ in possible expansion of h assign a score to h’ push h’ onto stack[len( h’ )] return max(stack[ n ]) CS 295: STATISTICAL NLP (WINTER 2017) 23

  24. Outline Decoding Algorithms Syntax-Based MT Neural MT Models CS 295: STATISTICAL NLP (WINTER 2017) 24

  25. Limits of the Phrase Model Ich habe das Auto gekauft Non-Contiguous Phrases I bought the car Den Antrag verabschiedet das Parlament Syntactic Transformations The draft approves the Parliament CS 295: STATISTICAL NLP (WINTER 2017) 25

  26. Syntax leads to Good English CS 295: STATISTICAL NLP (WINTER 2017) 26

  27. The Vauquios Triangle CS 295: STATISTICAL NLP (WINTER 2017) 27

  28. String to Tree Translation CS 295: STATISTICAL NLP (WINTER 2017) 28 [Yamada and Knight, 2001]

  29. String to Tree Translation CS 295: STATISTICAL NLP (WINTER 2017) 29

  30. Synchronous CFGs CS 295: STATISTICAL NLP (WINTER 2017) 30

  31. Outline Decoding Algorithms Syntax-Based MT Neural MT Models CS 295: STATISTICAL NLP (WINTER 2017) 31

  32. Neural MT Models CS 295: STATISTICAL NLP (WINTER 2017) 32

  33. Recurrent Neural Networks CS 295: STATISTICAL NLP (WINTER 2017) 33

  34. Recurrent Neural Networks Bee’s knees rodillas de abejas CS 295: STATISTICAL NLP (WINTER 2017) 34

  35. Different Weights Bee’s knees rodillas de abejas CS 295: STATISTICAL NLP (WINTER 2017) 35

  36. More Connections Bee’s knees rodillas de abejas CS 295: STATISTICAL NLP (WINTER 2017) 36

  37. CS 295: STATISTICAL NLP (WINTER 2017) 37

  38. Other Extensions Bee’s knees Reverse rodillas de abejas abejas de rodillas CS 295: STATISTICAL NLP (WINTER 2017) 38

  39. Other Extensions Bee’s knees Stacking rodillas de abejas CS 295: STATISTICAL NLP (WINTER 2017) 39

  40. Other Extensions Bi-directional de rodillas abejas Bee’s knees rodillas de abejas CS 295: STATISTICAL NLP (WINTER 2017) 40

  41. Regular Recurrent Units h t-1 h t x t CS 295: STATISTICAL NLP (WINTER 2017) 41

  42. Gated Recurrent Units h t-1 h t ĥ t r t z t x t CS 295: STATISTICAL NLP (WINTER 2017) 42

  43. Long Short-Term Memory h t-1 o t h t ĉ t c t-1 c t f t i t x t CS 295: STATISTICAL NLP (WINTER 2017) 43

  44. Neural MT Results CS 295: STATISTICAL NLP (WINTER 2017) 44

  45. Trend in Machine Translation CS 295: STATISTICAL NLP (WINTER 2017) 45

  46. Multilingual Neural MT: Naïve English-Spanish English-Spanish English Spanish Encoder Decoder English-Hindi English-Hindi English Hindi Encoder Decoder English-Chinese English-Chinese English Chinese Encoder Decoder CS 295: STATISTICAL NLP (WINTER 2017) 46

  47. Multilingual NMT: Decoder English-Spanish Spanish Encoder English-Hindi Shared English Hindi Encoder Decoder English-Chinese Chinese Encoder CS 295: STATISTICAL NLP (WINTER 2017) 47

  48. Multilingual NMT: Encoder English-Spanish Spanish Decoder English English-Hindi English Hindi Encoder Decoder English-Chinese Chinese Decoder CS 295: STATISTICAL NLP (WINTER 2017) 48

  49. Google Neural MT Spanish Spanish Spanish Encoder Spanish Decoder Hindi Hindi Encoder Hindi Decoder Hindi GNMT Chinese Chinese Encoder Chinese Decoder Chinese English English Encoder English Decoder English CS 295: STATISTICAL NLP (WINTER 2017) 49

  50. Out of Control! CS 295: STATISTICAL NLP (WINTER 2017) 50 From Ryan Cotterell @_shrdlu_

  51. Out of Control! CS 295: STATISTICAL NLP (WINTER 2017) 51 From Iain Murray @driainmurray

  52. Out of Control! CS 295: STATISTICAL NLP (WINTER 2017) 52 From Iain Murray @driainmurray

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

Machine Translation Contd Prof. Sameer Singh CS 295: STATISTICAL NLP WINTER 2017 March 2, 2017

Machine Translation Contd Prof. Sameer Singh CS 295: STATISTICAL NLP WINTER 2017 March 2, 2017

Machine Translation Contd Prof. Sameer Singh CS 295: STATISTICAL NLP WINTER 2017 March 2, 2017 Based on slides from Dan Klein, Philipp Koehn, Jacob Eisenstein, and everyone else they copied from. Omer Levy AI/ML Seminar Monday, March 6 th

1.04k views • 56 slides
Statistical Machine Translation Nadir Durrani 21-November-2014 Machine Translation

Statistical Machine Translation Nadir Durrani 21-November-2014 Machine Translation

Statistical Machine Translation Nadir Durrani 21-November-2014 Machine Translation www.uni-stuttart.de Problem: Automatic translation the foreign text: 2 Open Problems in Machine Translation www.uni-stuttart.de Ambiguity in translation

938 views • 44 slides
Machine Translation 2 Wikipedia Machine translation, often referred to by the acronym MT, is a

Machine Translation 2 Wikipedia Machine translation, often referred to by the acronym MT, is a

Machine Translation 2 Wikipedia Machine translation, often referred to by the acronym MT, is a sub-field of computational linguistics that investigates the use of computer software to translate text or speech from one natural language to

782 views • 24 slides
Machine Translation (M2M) Machine Translation (M2M) SNMP MIB to CIM MOF SNMP MIB to CIM MOF

Machine Translation (M2M) Machine Translation (M2M) SNMP MIB to CIM MOF SNMP MIB to CIM MOF

Machine Translation (M2M) Machine Translation (M2M) SNMP MIB to CIM MOF SNMP MIB to CIM MOF WIMS Working Group CIM Project 19 February 2007 PWG Maui Ira McDonald (High North) M2M Background Background M2M DMTF/PWG

437 views • 7 slides
Natural Language Processing Machine Translation Dan Klein UC Berkeley 1 Machine Translation 2

Natural Language Processing Machine Translation Dan Klein UC Berkeley 1 Machine Translation 2

Natural Language Processing Machine Translation Dan Klein UC Berkeley 1 Machine Translation 2 Machine Translation: Examples 3 Levels of Transfer 4 Word Level MT: Examples la politique de la haine . (Foreign Original) politics

675 views • 43 slides
Introd u ction to machine translation MAC H IN E TR AN SL ATION IN P YTH ON Th u shan

Introd u ction to machine translation MAC H IN E TR AN SL ATION IN P YTH ON Th u shan

Introd u ction to machine translation MAC H IN E TR AN SL ATION IN P YTH ON Th u shan Ganegedara Data Scientist and A u thor Machine translation MACHINE TRANSLATION IN PYTHON Machine translation MACHINE TRANSLATION IN PYTHON Co u rse o u

839 views • 38 slides
Natural Language Processing Machine Translation Machine Translation Dan Klein UC Berkeley

Natural Language Processing Machine Translation Machine Translation Dan Klein UC Berkeley

Natural Language Processing Machine Translation Machine Translation Dan Klein UC Berkeley Machine Translation: Examples Levels of Transfer Word Level MT: Examples Phrasal MT: Examples la politique de la haine . (Foreign Original)

222 views • 8 slides
Use of the Machine Translation Module within Dj Vu X2 Quick Guidance Introduction Machine

Use of the Machine Translation Module within Dj Vu X2 Quick Guidance Introduction Machine

Use of the Machine Translation Module within Dj Vu X2 Quick Guidance Introduction Machine Translation has now become incontrovertible in the translation industry. We at Atril put efforts in providing best help to the translation actors. In

393 views • 6 slides
Machine Translation Machine Translation February 13, 2008 Andreas Eisele UdS Computerlinguistik

Machine Translation Machine Translation February 13, 2008 Andreas Eisele UdS Computerlinguistik

Machine Translation Machine Translation February 13, 2008 Andreas Eisele UdS Computerlinguistik & DFKI eisele@dfki.de Foundations of Language Science and Technology WS 2007/8 Machine Translation: Overview Machine Translation: Overview

216 views • 21 slides
Machine Translation Machine Translation Berlin Chen 2003 References: 1. Natural Language

Machine Translation Machine Translation Berlin Chen 2003 References: 1. Natural Language

Machine Translation Machine Translation Berlin Chen 2003 References: 1. Natural Language Understanding, chapter 13 2. W. A. Gale and K. W. Church, A Program for Aligning Sentences in Bilingual Corpora, Computational Linguistics 1993 1

731 views • 34 slides
Machine Translation 12: (Non-neural) Statistical Machine Translation Rico Sennrich University of

Machine Translation 12: (Non-neural) Statistical Machine Translation Rico Sennrich University of

Machine Translation 12: (Non-neural) Statistical Machine Translation Rico Sennrich University of Edinburgh R. Sennrich MT 2018 12 1 / 27 Todays Lecture So far, main focus of lecture was on: neural machine translation research

740 views • 46 slides
Neural Machine Translation Gongbo Tang 8 October 2018 Outline Neural Machine Translation 1

Neural Machine Translation Gongbo Tang 8 October 2018 Outline Neural Machine Translation 1

Neural Machine Translation Gongbo Tang 8 October 2018 Outline Neural Machine Translation 1 Advances and Challenges 2 Gongbo Tang Neural Machine Translation 2/52 Neural Machine Translation Figure Recurrent neural network based NMT

906 views • 73 slides
Semi-supervised Learning for Neural Machine Translation Yong Cheng joint work with Wei Xu,

Semi-supervised Learning for Neural Machine Translation Yong Cheng joint work with Wei Xu,

Semi-supervised Learning for Neural Machine Translation Yong Cheng joint work with Wei Xu, Zhongjun He, Wei He, Hua Wu, Maosong Sun, Yang Liu 1 Machine Translation Automated translation using computer software 2 Machine Translation Rule-based

650 views • 26 slides
History & Evaluation CMSC 470 Marine Carpuat T odays topics Machine Translation

History & Evaluation CMSC 470 Marine Carpuat T odays topics Machine Translation

Machine Translation History & Evaluation CMSC 470 Marine Carpuat T odays topics Machine Translation Context: Historical Background Machine Translation is an old idea Machine Translation Evaluation 1947 When I look at an

825 views • 40 slides
Learning Non-Isomorphic Tree Mappings for Machine Translation Syntax-Based Machine Translation

Learning Non-Isomorphic Tree Mappings for Machine Translation Syntax-Based Machine Translation

Learning Non-Isomorphic Tree Mappings for Machine Translation Syntax-Based Machine Translation Jason Eisner - Johns Hopkins Univ. Previous work assumes essentially isomorphic trees Wu 1995, Alshawi et al. 2000, Yamada & Knight 2000

306 views • 5 slides
Introduction to Machine Translation CMSC 723 / LING 723 / INST 725 Marine Carpuat Slides &

Introduction to Machine Translation CMSC 723 / LING 723 / INST 725 Marine Carpuat Slides &

Introduction to Machine Translation CMSC 723 / LING 723 / INST 725 Marine Carpuat Slides & figure credits: Philipp Koehn mt-class.org T odays topics Machine Translation Historical Background Machine Translation is an old idea

1.17k views • 43 slides
Transformer Sequence Models CSE354 - Spring 2020 Natural Language Processing Most NLP Tasks.

Transformer Sequence Models CSE354 - Spring 2020 Natural Language Processing Most NLP Tasks.

Transformer Sequence Models CSE354 - Spring 2020 Natural Language Processing Most NLP Tasks. E.g. Transformer Networks Sequence Tasks Transformers Language Modeling BERT Machine Translation Speech

1.26k views • 105 slides
Lecture 13: Standard Modules CSE 140: Components and Design Techniques for Digital Systems Diba

Lecture 13: Standard Modules CSE 140: Components and Design Techniques for Digital Systems Diba

Lecture 13: Standard Modules CSE 140: Components and Design Techniques for Digital Systems Diba Mirza Dept. of Computer Science and Engineering University of California, San Diego 1 Decoder Application: universal set {Decoder, OR} Example:

311 views • 27 slides
CSE 140 Lecture 11 Standard Combinational Modules CK Cheng CSE Dept. UC San Diego 1 Part III

CSE 140 Lecture 11 Standard Combinational Modules CK Cheng CSE Dept. UC San Diego 1 Part III

CSE 140 Lecture 11 Standard Combinational Modules CK Cheng CSE Dept. UC San Diego 1 Part III - Standard Combinational Modules Introduction Decoder Behavior, Logic, Usage Encoder Multiplexer (Mux) Behavior, Logic,

301 views • 26 slides
A Hierarchical Encoder-Decoder for Paragraph Summarization Farzaneh Mahdisoltani Department of

A Hierarchical Encoder-Decoder for Paragraph Summarization Farzaneh Mahdisoltani Department of

A Hierarchical Encoder-Decoder for Paragraph Summarization Farzaneh Mahdisoltani Department of Computer Science University of Toronto CSC2541, Fall 2016 Farzaneh Mahdisoltani (University of Toronto) A Hierarchical Encoder-Decoder for

208 views • 8 slides
Memory Memory Decoders M bits M bits RWM NVRWM ROM S 0 S 0 Word 0 Word 0 S 1 Word 1 Word

Memory Memory Decoders M bits M bits RWM NVRWM ROM S 0 S 0 Word 0 Word 0 S 1 Word 1 Word

Memory Memory Decoders M bits M bits RWM NVRWM ROM S 0 S 0 Word 0 Word 0 S 1 Word 1 Word 1 A 0 S 2 Storage Storage Random Non-Random Word 2 Word 2 N Words Cell A 1 Cell EPROM Mask-Programmed Decoder Access Access E 2 PROM

464 views • 21 slides
AGL ARM prototype development update T oward the AGL spec 2.0 definition Hisao Munakata Linux

AGL ARM prototype development update T oward the AGL spec 2.0 definition Hisao Munakata Linux

Project outline Achievement (by Renesas) conclusion AGL ARM prototype development update T oward the AGL spec 2.0 definition Hisao Munakata Linux Foundation : Automotive Grade Linux June 2nd 2015 1 / 52 Hisao Munakata AGL ARM prototype

761 views • 52 slides
Data-Driven Ensembles for Deep and Hard-Decision Hybrid Decoding International Symposium on

Data-Driven Ensembles for Deep and Hard-Decision Hybrid Decoding International Symposium on

Introduction Introduction Introduction Data-Driven Ensembles for Deep and Hard-Decision Hybrid Decoding International Symposium on Information Theory Tomer Raviv Nir Raviv Yair Beery School of

645 views • 41 slides
Jet list decoding D. J. Bernstein University of Illinois at Chicago Thanks to: NSF 1018836

Jet list decoding D. J. Bernstein University of Illinois at Chicago Thanks to: NSF 1018836

Jet list decoding D. J. Bernstein University of Illinois at Chicago Thanks to: NSF 1018836 NIST 60NANB10D263 No thanks to: IEEE violating IEEE policies and forcing authors to take papers offline; see cr.yp.to/writing/ieee.html Decoding

885 views • 64 slides

More recommend