translation model adaptation using genre revealing text
play

Translation Model Adaptation Using Genre-Revealing Text Features - PowerPoint PPT Presentation

Mar 24, 2024 •18 likes •758 views

Translation Model Adaptation Using Genre-Revealing Text Features Marlies van der Wees, Arianna Bisazza, Christof Monz Domain adaptation for SMT Prioritize translation candidates that are most relevant to a specific task Translation Model

  1. Translation Model Adaptation Using Genre-Revealing Text Features Marlies van der Wees, Arianna Bisazza, Christof Monz

  2. Domain adaptation for SMT ✤ Prioritize translation candidates that are most relevant to a specific task Translation Model Adaptation 2 Using Genre-Revealing Text Features

  3. Domain adaptation for SMT ✤ Prioritize translation candidates that are most relevant to a specific task Heterogeneous training data Specific translation task Translation Model Adaptation 2 Using Genre-Revealing Text Features

  4. Domain adaptation for SMT ✤ Prioritize translation candidates that are most relevant to a specific task Heterogeneous training data Specific translation task Translation Model Adaptation 2 Using Genre-Revealing Text Features

  5. Domain adaptation for SMT ✤ Prioritize translation candidates that are most relevant to a specific task source p(f|e) p(e|f) … target Heterogeneous !ﻟﺣﻣ% & praise be to 0.1 0.2 … training data Specific !ﻟﺣﻣ% & praise for 0.2 0.2 … translation task thank 0.1 0.2 … !ﻟﺣﻣ% & ﺣﺑ(ﺑﺗﻲ + my dear 0.2 0.1 … my love 0.2 0.1 … ﺣﺑ(ﺑﺗﻲ + ﺣﺑ(ﺑﺗﻲ + my sweetheart 0.1 0.1 … Translation Model Adaptation 2 Using Genre-Revealing Text Features

  6. Domain adaptation for SMT ✤ Prioritize translation candidates that are most relevant to a specific task source source p(f|e) p(e|f) … p(f|e) p(e|f) … target target Heterogeneous !ﻟﺣﻣ% & !ﻟﺣﻣ% & praise be to praise be to 0.1 0.2 … 0.1 0.2 … training data Specific !ﻟﺣﻣ% & !ﻟﺣﻣ% & praise for praise for 0.2 0.2 … 0.2 0.2 … translation task thank thank 0.1 0.2 … 0.1 0.2 … !ﻟﺣﻣ% & !ﻟﺣﻣ% & ﺣﺑ(ﺑﺗﻲ + ﺣﺑ(ﺑﺗﻲ + my dear my dear 0.2 0.1 … 0.2 0.1 … my love my love 0.2 0.1 … 0.2 0.1 … ﺣﺑ(ﺑﺗﻲ + ﺣﺑ(ﺑﺗﻲ + ﺣﺑ(ﺑﺗﻲ + ﺣﺑ(ﺑﺗﻲ + my sweetheart my sweetheart 0.1 0.1 … 0.1 0.1 … Translation Model Adaptation 2 Using Genre-Revealing Text Features

  7. Domain adaptation for SMT ✤ Prioritize translation candidates that are most relevant to a specific task source source p(f|e) p(e|f) … p(f|e) p(e|f) … target target Heterogeneous !ﻟﺣﻣ% & !ﻟﺣﻣ% & praise be to praise be to 0.1 0.2 … 0.1 0.2 … training data Specific !ﻟﺣﻣ% & !ﻟﺣﻣ% & praise for praise for 0.2 0.2 … 0.2 0.2 … translation task thank thank 0.1 0.2 … 0.1 0.2 … !ﻟﺣﻣ% & !ﻟﺣﻣ% & ﺣﺑ(ﺑﺗﻲ + ﺣﺑ(ﺑﺗﻲ + my dear my dear 0.2 0.1 … 0.2 0.1 … my love my love 0.2 0.1 … 0.2 0.1 … ﺣﺑ(ﺑﺗﻲ + ﺣﺑ(ﺑﺗﻲ + ﺣﺑ(ﺑﺗﻲ + ﺣﺑ(ﺑﺗﻲ + my sweetheart my sweetheart 0.1 0.1 … 0.1 0.1 … ✤ What type of domain information to use? Translation Model Adaptation 2 Using Genre-Revealing Text Features

  8. Dimensions of domains ✤ Topic refers to general subject politics, sports, tennis ✦ Translation Model Adaptation 3 Using Genre-Revealing Text Features

  9. Dimensions of domains ✤ Topic refers to general subject politics, sports, tennis ✦ ✤ Genre refers to function, style, text type editorials, newswire, user-generated text ✦ orthogonal to topic ✦ Translation Model Adaptation 3 Using Genre-Revealing Text Features

  10. Dimensions of domains ✤ Topic refers to general subject politics, sports, tennis ✦ ✤ Genre refers to function, style, text type editorials, newswire, user-generated text ✦ orthogonal to topic ✦ ✤ Provenance refers to document’s origin LDC2005T13, Europarl, EMEA ✦ Translation Model Adaptation 3 Using Genre-Revealing Text Features

  11. The problem with provenance Provenance information has proven useful for adaptation in SMT, but is it the best representation of a domain? Translation Model Adaptation 4 Using Genre-Revealing Text Features

  12. The problem with provenance Provenance information has proven useful for adaptation in SMT, but is it the best representation of a domain? ✤ It’s not an intrinsic text property Translation Model Adaptation 4 Using Genre-Revealing Text Features

  13. The problem with provenance Provenance information has proven useful for adaptation in SMT, but is it the best representation of a domain? ✤ It’s not an intrinsic text property ✤ We might need manual labeling labor-intensive ✦ arbitrary ✦ Translation Model Adaptation 4 Using Genre-Revealing Text Features

  14. The problem with provenance Provenance information has proven useful for adaptation in SMT, but is it the best representation of a domain? ✤ It’s not an intrinsic text property ✤ We might need manual labeling labor-intensive ✦ arbitrary ✦ ✤ Often combines particular topic and genre Translation Model Adaptation 4 Using Genre-Revealing Text Features

  15. Disentangling topic and genre in SMT* ✤ Experiments on News Comment controlled test set: The 12 contestants You allowed Barwas Culture competed during a to represent Iraq Gen&Topic May 3rd Prime. while she sings in Kurdish!!! Economy Yemen is mulling What development the establishment of in Yemen are you 13 industrial zones. talking about? Translation Model Adaptation * Van der Wees et al., 2015 5 Using Genre-Revealing Text Features

  16. Disentangling topic and genre in SMT* ✤ Experiments on News Comment controlled test set: The 12 contestants You allowed Barwas Culture competed during a to represent Iraq Gen&Topic May 3rd Prime. while she sings in ✤ Genre has larger Kurdish!!! impact on SMT than topic Economy Yemen is mulling What development the establishment of in Yemen are you 13 industrial zones. talking about? Translation Model Adaptation * Van der Wees et al., 2015 5 Using Genre-Revealing Text Features

  17. Disentangling topic and genre in SMT* ✤ Experiments on News Comment controlled test set: The 12 contestants You allowed Barwas Culture competed during a to represent Iraq Gen&Topic May 3rd Prime. while she sings in ✤ Genre has larger Kurdish!!! impact on SMT than topic Economy Yemen is mulling What development the establishment of in Yemen are you ✤ We want to adapt 13 industrial zones. talking about? to different genres in a test corpus! Translation Model Adaptation * Van der Wees et al., 2015 5 Using Genre-Revealing Text Features

  18. What information to use for adaptation? ✤ Provenance information manual grouping of sub-corpora ✦ Translation Model Adaptation 6 Using Genre-Revealing Text Features

  19. What information to use for adaptation? ✤ Provenance information manual grouping of sub-corpora ✦ ✤ Topic information unsupervised LDA-inferred topics ✦ Translation Model Adaptation 6 Using Genre-Revealing Text Features

  20. What information to use for adaptation? ✤ Provenance information manual grouping of sub-corpora ✦ ✤ Topic information unsupervised LDA-inferred topics ✦ ✤ Genre information determine and exploit intrinsic ✦ genre-revealing text features Translation Model Adaptation 6 Using Genre-Revealing Text Features

  21. What information to use for adaptation? ✤ Provenance information manual grouping of sub-corpora ✦ ✤ Topic information unsupervised LDA-inferred topics ✦ ✤ Genre information determine and exploit intrinsic ✦ genre-revealing text features Translation Model Adaptation 6 Using Genre-Revealing Text Features

  22. What information to use for adaptation? ✤ Provenance information manual grouping of sub-corpora ✦ ✤ Topic information unsupervised LDA-inferred topics ✦ ✤ Genre information determine and exploit intrinsic ✦ genre-revealing text features Translation Model Adaptation 6 Using Genre-Revealing Text Features

  23. What information to use for adaptation? ✤ Provenance information manual grouping of sub-corpora ✦ ✤ Topic information unsupervised LDA-inferred topics ✦ ✤ Genre information determine and exploit intrinsic ✦ genre-revealing text features Translation Model Adaptation 6 Using Genre-Revealing Text Features

  24. Genre adaptation: the task ✤ Arabic-English phrase-based SMT Translation Model Adaptation * ilps.science.uva.nl/resources/gen-topic/ 7 Using Genre-Revealing Text Features

  25. Genre adaptation: the task ✤ Arabic-English phrase-based SMT ✤ Two multi-genre evaluation sets: Gen&Topic*: ✦ newswire (NW) • comments (UG) • Translation Model Adaptation * ilps.science.uva.nl/resources/gen-topic/ 7 Using Genre-Revealing Text Features

  26. Genre adaptation: the task ✤ Arabic-English phrase-based SMT ✤ Two multi-genre evaluation sets: Gen&Topic*: NIST: ✦ ✦ newswire (NW) newswire (NW) • • comments (UG) weblogs (UG) • • Translation Model Adaptation * ilps.science.uva.nl/resources/gen-topic/ 7 Using Genre-Revealing Text Features

  27. Genre adaptation: the task ✤ Arabic-English phrase-based SMT ✤ Two multi-genre evaluation sets: Gen&Topic*: NIST: ✦ ✦ newswire (NW) newswire (NW) • • comments (UG) weblogs (UG) • • ✤ Translation model adaptation Translation Model Adaptation * ilps.science.uva.nl/resources/gen-topic/ 7 Using Genre-Revealing Text Features

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

Presenter: Farah Adeeba What is Genre How to Define Genre Urdu Text Genre

Presenter: Farah Adeeba What is Genre How to Define Genre Urdu Text Genre

Presenter: Farah Adeeba What is Genre How to Define Genre Urdu Text Genre Identification Automated genre classification is concerned with predicting the genre of an unknown text correctly, independent of its topic, style or any

414 views • 29 slides
Book of the Month Is this a fiction or non-fiction text? How do you know which genre it

Book of the Month Is this a fiction or non-fiction text? How do you know which genre it

Januarys Principals Book of the Month Is this a fiction or non-fiction text? How do you know which genre it belongs to? What specific features in this text indicate the genre? What is your favorite genre of book to read

384 views • 10 slides
Assessing Genre and Method Variation in Translation Using Computational Techniques Ekaterina

Assessing Genre and Method Variation in Translation Using Computational Techniques Ekaterina

Assessing Genre and Method Variation in Translation Using Computational Techniques Ekaterina Lapshinova-Koltunski and Marcos Zampieri Paris 16 January 2015 16 January 2015 Genre and Method Variation in Translation 1 Overview Aims and

622 views • 38 slides
Translation Model Interpolation for Domain Adaptation in TectoMT Charles University in Prague

Translation Model Interpolation for Domain Adaptation in TectoMT Charles University in Prague

Rudolf Rosa , Ondej Duek, Michal Novk, Martin Popel {rosa,odusek,mnovak,popel}@ufal.mff.cuni.cz Translation Model Interpolation for Domain Adaptation in TectoMT Charles University in Prague Faculty of Mathematics and Physics Institute

561 views • 29 slides
Film Noir An American Film Genre with a French Name Film Noir Literal translation=black

Film Noir An American Film Genre with a French Name Film Noir Literal translation=black

http://blog.ctnews.com/meyers/files/2010/07/noir4.jpg Film Noir An American Film Genre with a French Name Film Noir Literal translation=black film (Barsam 86) American genre named by French critic Named for its dark tone and

587 views • 26 slides
Investigations on Translation Model Adaptation Using Monolingual Data Patrik Lambert, Holger

Investigations on Translation Model Adaptation Using Monolingual Data Patrik Lambert, Holger

Investigations on Translation Model Adaptation Using Monolingual Data Patrik Lambert, Holger Schwenk Christophe Servan and Sadaf Abdul-Rauf LIUM (Computing Laboratory) University of Le Mans France WMT 2011 Lambert, Schwenk, Servan, Abdul-Rauf

485 views • 30 slides
Unsupervised Machine Translation Sachin Kumar Conditional Text Generation Generate text

Unsupervised Machine Translation Sachin Kumar Conditional Text Generation Generate text

CMU CS11-737: Multilingual NLP (Fall 2020) Unsupervised Machine Translation Sachin Kumar Conditional Text Generation Generate text according to a specification: P(Y|X) Input X Output Y (Text) Task English Hindi Machine Translation

743 views • 35 slides
Adaptation Philipp Koehn 27 October 2020 Philipp Koehn Machine Translation: Adaptation 27

Adaptation Philipp Koehn 27 October 2020 Philipp Koehn Machine Translation: Adaptation 27

Adaptation Philipp Koehn 27 October 2020 Philipp Koehn Machine Translation: Adaptation 27 October 2020 Adaptation 1 Better quality when system is adapted to a task Domain adaptation to a specific domain, e.g., information technology

962 views • 46 slides
Hybrid Adaptation of Named Entity Recognition for Statistical Machine Translation Vassilina

Hybrid Adaptation of Named Entity Recognition for Statistical Machine Translation Vassilina

Hybrid Adaptation of Named Entity Recognition for Statistical Machine Translation Vassilina Nikoulina, gnes Sndor, Marc Dymetman Outline Introduction Approach NER integration within SMT NER adaptation for SMT NER prediction for

567 views • 15 slides
Hybrid Adaptation of Named Entity Recognition for Statistical Machine Translation Vassilina

Hybrid Adaptation of Named Entity Recognition for Statistical Machine Translation Vassilina

Hybrid Adaptation of Named Entity Recognition for Statistical Machine Translation Vassilina Nikoulina, gnes Sndor, Marc Dymetman Outline Introduction Approach NER integration within SMT NER adaptation for SMT NER prediction for

403 views • 15 slides
Measuring Immediate Adaptation Performance for Neural Machine Translation Patrick Simianer , Joern

Measuring Immediate Adaptation Performance for Neural Machine Translation Patrick Simianer , Joern

Measuring Immediate Adaptation Performance for Neural Machine Translation Patrick Simianer , Joern Wuebker, John DeNero Lilt NAACL 19 Outline Motivation & Approach 1 2 Evaluation Conclusion 3 2 / 20 Motivation Online adaptation is

765 views • 52 slides
Machine Translation Dan Klein, John DeNero UC Berkeley Translation Task Text as input &

Machine Translation Dan Klein, John DeNero UC Berkeley Translation Task Text as input &

Machine Translation Dan Klein, John DeNero UC Berkeley Translation Task Text as input & text as output. Input & output have roughly the same information content. Output is more predictable than a language modeling task.

649 views • 30 slides
ISCTM Recommendations on the Translation and Adaptation of Clinician Reported Outcomes in

ISCTM Recommendations on the Translation and Adaptation of Clinician Reported Outcomes in

ISCTM Recommendations on the Translation and Adaptation of Clinician Reported Outcomes in International Clinical Trials Elizabeth Pappadopulos PHD, Global CNS Lead - Pfizer Objective The ISCTM guidelines are intended to provide practical

592 views • 17 slides
Domain Adaptation in Statistical Machine Translation Logic, Language and Computation Bart

Domain Adaptation in Statistical Machine Translation Logic, Language and Computation Bart

Domain Adaptation in Statistical Machine Translation Logic, Language and Computation Bart Mellebeek October 28, 2013 Bart Mellebeek Domain Adaptation in Statistical Machine Translation Outline Machine Translation and AI Statistical Machine

889 views • 54 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
Share of proceeds Overall mitigation of global emissions SOP for adaptation in 6.4 text VII.

Share of proceeds Overall mitigation of global emissions SOP for adaptation in 6.4 text VII.

Share of proceeds Overall mitigation of global emissions SOP for adaptation in 6.4 text VII. Levy of share of proceeds for adaptation [and administrative expenses] 74. The SOP from an Art. 6.4 activity for .. needs of PV countries shall

185 views • 16 slides
Mary Southern and Gopalan Nadathur Department of Computer Science and Engineering University of

Mary Southern and Gopalan Nadathur Department of Computer Science and Engineering University of

A Translation-Based Animation of Dependently-Typed Specifications From LF to hohh (and back again) Mary Southern and Gopalan Nadathur Department of Computer Science and Engineering University of Minnesota This work was funded by NSF grant

668 views • 24 slides
Optimizing Binary Translation of Dynamically Generated Code Byron Hawkins Brian Demsky

Optimizing Binary Translation of Dynamically Generated Code Byron Hawkins Brian Demsky

Optimizing Binary Translation of Dynamically Generated Code Byron Hawkins Brian Demsky University of California, Irvine Derek Bruening Qin Zhao Google, Inc. Profiling Bug detection Program analysis Security SPEC CPU 2006

1.15k views • 85 slides
Parser Self-Training for Syntax-Based Machine Translation Nara Institute of Science and

Parser Self-Training for Syntax-Based Machine Translation Nara Institute of Science and

Parser Self-Training for Syntax-Based Machine Translation Nara Institute of Science and Technology Augmented Human Communication Laboratory Makoto Morishita, Koichi Akabe, Yuto Hatakoshi, Graham Neubig, Koichiro Yoshino, Satoshi

632 views • 37 slides
Order and Report Schema Translation in WISE-SBML Server Dr. Mark Pullen Dr. Per Gustavsson Dr.

Order and Report Schema Translation in WISE-SBML Server Dr. Mark Pullen Dr. Per Gustavsson Dr.

Order and Report Schema Translation in WISE-SBML Server Dr. Mark Pullen Dr. Per Gustavsson Dr. Robert Wittman Douglas Corner Saab AB MITRE Corp. per.m.gustavsson@ rwittman@mitre.org GMU C4I Center saabgroup.com mpullen@c4i.gmu.edu

404 views • 27 slides
CS356 Unit 9 Virtual Memory & Address Translation 9.2 Indirection Indirection means

CS356 Unit 9 Virtual Memory & Address Translation 9.2 Indirection Indirection means

9.1 CS356 Unit 9 Virtual Memory & Address Translation 9.2 Indirection Indirection means using one entity to refer to another Examples: A variable name vs. it's physical memory address Phone number vs. cell tower

844 views • 53 slides
Source Address Finding (SAF) for IPv6 Translation Mechanisms draft-thaler-ipv6-saf-01.txt Dave

Source Address Finding (SAF) for IPv6 Translation Mechanisms draft-thaler-ipv6-saf-01.txt Dave

Source Address Finding (SAF) for IPv6 Translation Mechanisms draft-thaler-ipv6-saf-01.txt Dave Thaler dthaler@microsoft.com IETF 74 - 6AI BOF 1 UNilateral Self-Address Fixing (UNSAF) 1:1 address mappings (NAT66) avoid most of the issues

545 views • 7 slides
Predicate Logic: Introduction and Translations Alice Gao Lecture 11 CS 245 Logic and

Predicate Logic: Introduction and Translations Alice Gao Lecture 11 CS 245 Logic and

Predicate Logic: Introduction and Translations Alice Gao Lecture 11 CS 245 Logic and Computation Fall 2019 1 / 37 Outline Learning goals Introduction and Motivation Elements of Predicate Logic Translating between English and Predicate

604 views • 37 slides
Certificate Translation for Specification Preserving Advices Gilles Barthe and Csar Kunz INRIA

Certificate Translation for Specification Preserving Advices Gilles Barthe and Csar Kunz INRIA

Certificate Translation for Specification Preserving Advices Certificate Translation for Specification Preserving Advices Gilles Barthe and Csar Kunz INRIA Sophia Antipolis - Mditerrane FOAL 2008 Csar Kunz (with Gilles Barthe) FOAL

481 views • 44 slides

More recommend