the sigmorphon 2016 shared task morphological reinflection
play

The SIGMORPHON 2016 shared task morphological reinflection Ryan - PowerPoint PPT Presentation

Nov 14, 2023 •531 likes •1.28k views

The SIGMORPHON 2016 shared task morphological reinflection Ryan Cotterell, Christo Kirov, John Sylak-Glassman, David Yarowsky, Jason Eisner, Mans Hulden 1 SIGMORPHON 2016 Shared task - morphological reinflection Shared task

  1. The SIGMORPHON 2016 shared task— morphological reinflection Ryan Cotterell, Christo Kirov, John Sylak-Glassman, David Yarowsky, Jason Eisner, Mans Hulden 1 SIGMORPHON 2016 Shared task - morphological reinflection

  2. Shared task ‣ SIGMORPHON’s first shared task! ‣ First shared task on supervised learning of (inflectional) morphology ‣ featuring … • 3 tasks • 3 “tracks” • 10 languages • 9 systems submitted 2 SIGMORPHON 2016 Shared task - morphological reinflection

  3. Shared task Overview ‣ Tasks [MH] ‣ Language data [CK] ‣ Systems overview & results [RC] 3 SIGMORPHON 2016 Shared task - morphological reinflection

  4. Shared task Tasks ‣ 1 Inflection (synthesis/generation) ‣ 2 Reinflection (analysis + synthesis) ‣ 3 Unlabeled Reinflection 4 SIGMORPHON 2016 Shared task - morphological reinflection

  5. Task 1(inflection) train lemma MSD (feature/value pairs) word form test 5 SIGMORPHON 2016 Shared task - morphological reinflection

  6. Task 1(inflection) train lemma MSD (feature/value pairs) word form run test 6 SIGMORPHON 2016 Shared task - morphological reinflection

  7. Task 1(inflection) train lemma MSD (feature/value pairs) word form run pos=V,mood=IND,tense=PST,per=3,num=SG test 7 SIGMORPHON 2016 Shared task - morphological reinflection

  8. Task 1(inflection) train lemma MSD (feature/value pairs) word form run pos=V,mood=IND,tense=PST,per=3,num=SG ran test 8 SIGMORPHON 2016 Shared task - morphological reinflection

  9. Task 1(inflection) train lemma MSD (feature/value pairs) word form run pos=V,mood=IND,tense=PST,per=3,num=SG ran love pos=V,tense=PRS loving eat pos=V,mood=IND,tense=PST,per=1,num=SG ate … test 9 SIGMORPHON 2016 Shared task - morphological reinflection

  10. Task 1(inflection) train lemma MSD (feature/value pairs) word form run pos=V,mood=IND,tense=PST,per=3,num=SG ran love pos=V,tense=PRS loving eat pos=V,mood=IND,tense=PST,per=1,num=SG ate … test hate pos=V,tense=PRS ? 10 SIGMORPHON 2016 Shared task - morphological reinflection

  11. Task 1(inflection) train lemma MSD (feature/value pairs) word form run pos=V,mood=IND,tense=PST,per=3,num=SG ran love pos=V,tense=PRS loving eat pos=V,mood=IND,tense=PST,per=1,num=SG ate … test hate pos=V,tense=PRS ? read pos=V,mood=IND,tense=PST,per=3,num=SG ? 11 SIGMORPHON 2016 Shared task - morphological reinflection

  12. Task 1(inflection) train lemma MSD (feature/value pairs) word form run pos=V,mood=IND,tense=PST,per=3,num=SG ran love pos=V,tense=PRS loving eat pos=V,mood=IND,tense=PST,per=1,num=SG ate … test hate pos=V,tense=PRS hating read pos=V,mood=IND,tense=PST,per=3,num=SG read 12 SIGMORPHON 2016 Shared task - morphological reinflection

  13. Training data 13 SIGMORPHON 2016 Shared task - morphological reinflection

  14. Training data 14 SIGMORPHON 2016 Shared task - morphological reinflection

  15. Training data schreiben pos=V,mood={OPT/SBJV},tense=PRS,per=1,num=PL schreiben 15 SIGMORPHON 2016 Shared task - morphological reinflection

  16. Task 2 (reinflection) train MSD1 form1 MSD2 form2 test 16 SIGMORPHON 2016 Shared task - morphological reinflection

  17. Task 2 (reinflection) train MSD1 form1 MSD2 form2 pos=V,tense=PRS running pos=V,tense=PST ran test 17 SIGMORPHON 2016 Shared task - morphological reinflection

  18. Task 2 (reinflection) train MSD1 form1 MSD2 form2 pos=V,tense=PRS running pos=V,tense=PST ran … test pos=V,tense=PST sought pos=V,tense=INF 18 SIGMORPHON 2016 Shared task - morphological reinflection

  19. Task 2 (reinflection) train MSD1 form1 MSD2 form2 pos=V,tense=PRS running pos=V,tense=PST ran … test pos=V,tense=PST sought pos=V,tense=INF ? … 19 SIGMORPHON 2016 Shared task - morphological reinflection

  20. Task 2 (reinflection) train MSD1 form1 MSD2 form2 pos=V,tense=PRS running pos=V,tense=PST ran … test pos=V,tense=PST sought pos=V,tense=INF seek … 20 SIGMORPHON 2016 Shared task - morphological reinflection

  21. Task 3 (unlabeled reinflection) train MSD1 form1 MSD2 form2 pos=V,tense=PRS running pos=V,tense=PST ran … test pos=V,tense=PST sought pos=V,tense=INF seek … 21 SIGMORPHON 2016 Shared task - morphological reinflection

  22. Task 3 (unlabeled reinflection) train MSD1 form1 MSD2 form2 pos=V,tense=PRS running pos=V,tense=PST ran … test pos=V,tense=PST sought pos=V,tense=INF seek … 22 SIGMORPHON 2016 Shared task - morphological reinflection

  23. Task 3 (unlabeled reinflection) train form1 MSD2 form2 running pos=V,tense=PST ran … test sought pos=V,tense=INF seek … 23 SIGMORPHON 2016 Shared task - morphological reinflection

  24. Summary of tasks 24 SIGMORPHON 2016 Shared task - morphological reinflection

  25. Summary of tasks auto Lemma > inflection Task 1 Finnish 25 SIGMORPHON 2016 Shared task - morphological reinflection

  26. Summary of tasks auto Lemma > inflection Task 1 Finnish 26 SIGMORPHON 2016 Shared task - morphological reinflection

  27. Summary of tasks auto inflection > inflection Task 2 Finnish 27 SIGMORPHON 2016 Shared task - morphological reinflection

  28. Summary of tasks auto inflection > inflection Task 2 Finnish 28 SIGMORPHON 2016 Shared task - morphological reinflection

  29. Summary of tasks auto unk > inflection Task 3 Finnish ? autona 29 SIGMORPHON 2016 Shared task - morphological reinflection

  30. Summary of tasks auto unk > inflection Task 3 Finnish ? autona 30 SIGMORPHON 2016 Shared task - morphological reinflection

  31. Summary of tasks auto unk > inflection Task 3 Finnish autona 31 SIGMORPHON 2016 Shared task - morphological reinflection

  32. Summary of tasks auto inflection > inflection Task 2 (reduction) Finnish 32 SIGMORPHON 2016 Shared task - morphological reinflection

  33. Summary of tasks auto inflection > inflection Task 2 (reduction) Finnish 33 SIGMORPHON 2016 Shared task - morphological reinflection

  34. Summary of tasks auto inflection > inflection Task 2 (reduction) Finnish 34 SIGMORPHON 2016 Shared task - morphological reinflection

  35. Summary of tasks auto unk > inflection Task 3 (reduction) Finnish autona 35 SIGMORPHON 2016 Shared task - morphological reinflection

  36. Summary of tasks auto unk > inflection Task 3 (reduction) Finnish autona 36 SIGMORPHON 2016 Shared task - morphological reinflection

  37. Summary of tasks auto unk > inflection Task 3 (reduction) Finnish autona 37 SIGMORPHON 2016 Shared task - morphological reinflection

  38. Summary of tasks auto unk > inflection Task 3 (reduction) Finnish autona 38 SIGMORPHON 2016 Shared task - morphological reinflection

  39. Tracks Restricted Standard Bonus Task 1 1 1 1, M Task 2 2 1, 2 1, 2, M Task 3 3 1, 2, 3 1, 2, 3, M 39 SIGMORPHON 2016 Shared task - morphological reinflection

  40. Tracks Restricted Standard Bonus Task 1 1 1 1, M Task 2 2 1, 2 1, 2, M Task 3 3 1, 2, 3 1, 2, 3, M can reduce 40 SIGMORPHON 2016 Shared task - morphological reinflection

  41. Tracks Restricted Standard Bonus Task 1 1 1 1, M Task 2 2 1, 2 1, 2, M Task 3 3 1, 2, 3 1, 2, 3, M can’t reduce can reduce 41 SIGMORPHON 2016 Shared task - morphological reinflection

  42. Tracks Restricted Standard Bonus Task 1 1 1 1, M Task 2 2 1, 2 1, 2, M Task 3 3 1, 2, 3 1, 2, 3, M can reduce+ can’t reduce can reduce raw text dumps 42 SIGMORPHON 2016 Shared task - morphological reinflection

  43. Evaluation Three types, averaged over all inputs ‣ Accuracy (0/1) ‣ Levenshtein distance to gold form ‣ Reciprocal rank (for multiple guesses) -1/rank i (rank i = position of gold form among guesses) 43 SIGMORPHON 2016 Shared task - morphological reinflection

  44. Baseline ‣ Simple discriminative string transduction (similar to recent work*) ‣ Classifier is averaged perceptron ‣ Applies greedy labeling of input characters, given target features + features of surrounding characters, previous decisions *Durrett & DeNero (2013), Nicolai et al (2015) 44 SIGMORPHON 2016 Shared task - morphological reinflection

  45. Baseline source = [pos=V,tense=PRES…] target = lemma input # r u n s # P classification REPT output r 45 SIGMORPHON 2016 Shared task - morphological reinflection

  46. Baseline source = [pos=V,tense=PRES…] target = lemma input # r u n s # P classification REPT REPT output r u 46 SIGMORPHON 2016 Shared task - morphological reinflection

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

LAW-MWE-CxG 2018 Shared task poster boosters 1. DEEP-BGT AT PARSEME SHARED TASK 2018:

LAW-MWE-CxG 2018 Shared task poster boosters 1. DEEP-BGT AT PARSEME SHARED TASK 2018:

LAW-MWE-CxG 2018 Shared task poster boosters 1. DEEP-BGT AT PARSEME SHARED TASK 2018: BIDIRECTIONAL LSTM- CRF MODEL FOR VERBAL MULTIWORD EXPRESSION IDENTIFICATION, Gzde Berk, Berna Erden and Tunga Gungor 2. GBD-NER AT PARSEME SHARED TASK

555 views • 14 slides
Feature-Based Tagging The Task, Again Recall: tagging ~ morphological disambiguation

Feature-Based Tagging The Task, Again Recall: tagging ~ morphological disambiguation

Feature-Based Tagging The Task, Again Recall: tagging ~ morphological disambiguation tagset V T (C 1 ,C 2 ,...C n ) C i - morphological categories, such as POS, NUMBER, CASE, PERSON, TENSE, GENDER, ... mapping w {t

418 views • 16 slides
Shared Governance Task Force Report https://web.ramapo.edu/shared-governance-task-force/ 1

Shared Governance Task Force Report https://web.ramapo.edu/shared-governance-task-force/ 1

4/4/2018 Ramapo College of New Jersey Shared Governance Task Force Report https://web.ramapo.edu/shared-governance-task-force/ 1 Overview of Preliminary Report How Did We Get Here? The Charge to the Shared Governance Task Force (SGTF)

228 views • 9 slides
The PARSEME Shared Task on Automatic Identification of Verbal Multiword Expressions (1.1) C.

The PARSEME Shared Task on Automatic Identification of Verbal Multiword Expressions (1.1) C.

Context Annotation methodology Corpora Shared task Wrapping up The PARSEME Shared Task on Automatic Identification of Verbal Multiword Expressions (1.1) C. Ramisch 1 , S. Ricardo 1 , A. Savary 2 , V. Vincze 3 , V. Barbu 4 , A. Bhatia 5 , M.

1.02k views • 25 slides
WMT 2016 Shared Task on Cross-lingual Pronoun Prediction . Liane Guillou, Christian Hardmeier,

WMT 2016 Shared Task on Cross-lingual Pronoun Prediction . Liane Guillou, Christian Hardmeier,

. WMT 2016 Shared Task on Cross-lingual Pronoun Prediction . Liane Guillou, Christian Hardmeier, Preslav Nakov, Sara Stymne, J org Tiedemann, Yannick Versley, Mauro Cettolo, Bonnie Webber and Andrei Popescu-Belis 12/08/2016 Cross-lingual

296 views • 16 slides
Results of the WMT16 Metrics Shared Task Ond rej Bojar Yvette Graham Amir Kamran Milo s

Results of the WMT16 Metrics Shared Task Ond rej Bojar Yvette Graham Amir Kamran Milo s

Results of the WMT16 Metrics Shared Task Ond rej Bojar Yvette Graham Amir Kamran Milo s Stanojevi c WMT16, Aug 11, 2016 1 / 32 Overview Summary of Metrics Task. Updates to Metric Task in 2016. Results 2 / 32 Metrics

634 views • 45 slides
DPIL@FIRE 2016: Overview of Shared Task on Detecting Paraphrases in Indian Languages (DPIL) M.

DPIL@FIRE 2016: Overview of Shared Task on Detecting Paraphrases in Indian Languages (DPIL) M.

DPIL@FIRE 2016: Overview of Shared Task on Detecting Paraphrases in Indian Languages (DPIL) M. Anand Kumar, Shivkaran Singh, Kavirajan B, and Soman K P Center for Computational Engg and Networking, Amrita Vishwa Vidyapetham, Coimbatore

213 views • 18 slides
WMT 10 Shared Tasks: Translation Task System Combination Task Chris Callison-Burch, Philipp

WMT 10 Shared Tasks: Translation Task System Combination Task Chris Callison-Burch, Philipp

WMT 10 Shared Tasks: Translation Task System Combination Task Chris Callison-Burch, Philipp Koehn, Christof Monz, Omar Zaidan 15 July 2010 Philipp Koehn WMT10 Shared Tasks 15 July 2010 Translation Task 1 Open benchmark for machine

662 views • 37 slides
UNSUPERVISED MORPHOLOGICAL SEGMENTATION & CLUSTERING ICL UNI HEIDELBERG - HS CL4LRL -

UNSUPERVISED MORPHOLOGICAL SEGMENTATION & CLUSTERING ICL UNI HEIDELBERG - HS CL4LRL -

UNSUPERVISED MORPHOLOGICAL SEGMENTATION & CLUSTERING ICL UNI HEIDELBERG - HS CL4LRL - KATHARINA ALLGAIER - 08.06.2016 1 OVERVIEW Introduction Morphological Segmentation (Creutz&Lagus 2005) Aims Models

762 views • 24 slides
Modeling Unrestricted Coreference in OntoNotes CoNLL-2011 Shared Task Sameer S Pradhan 1 Lance

Modeling Unrestricted Coreference in OntoNotes CoNLL-2011 Shared Task Sameer S Pradhan 1 Lance

CoNLL Shared Task OntoNotes Evaluation Modeling Unrestricted Coreference in OntoNotes CoNLL-2011 Shared Task Sameer S Pradhan 1 Lance Ramshaw 1 Mitchell Marcus 2 Martha Palmer 3 Ralph Weischedel 1 Nianwen Xue 4 1 BBN Technologies, Cambridge, MA

1.17k views • 70 slides
A New Universal Morphological Feature Schema for Rich Morphological Annotation and Cross-Lingual

A New Universal Morphological Feature Schema for Rich Morphological Annotation and Cross-Lingual

A New Universal Morphological Feature Schema for Rich Morphological Annotation and Cross-Lingual Projection John Sylak-Glassman, Christo Kirov, Matt Post, Roger Que, David Yarowsky (PI) Center for Language and Speech Processing Johns Hopkins

770 views • 20 slides
Results of the WMT16 Tuning Shared Task 1 Bushra Jawaid 1 Amir Kamran 1 Milo

Results of the WMT16 Tuning Shared Task 1 Bushra Jawaid 1 Amir Kamran 1 Milo

Results of the WMT16 Tuning Shared Task 1 Bushra Jawaid 1 Amir Kamran 1 Milo Stojanovi 2 Ond ej Bojar 1 ILLC, University of Amsterdam 2 MFF UFAL, Charles University in Prague WMT16, Aug 11, 2016 Overview

685 views • 24 slides
Results of the WMT19 Metrics Shared Task Segment-Level and Strong MT Systems Pose Big Challenges

Results of the WMT19 Metrics Shared Task Segment-Level and Strong MT Systems Pose Big Challenges

Results of the WMT19 Metrics Shared Task Segment-Level and Strong MT Systems Pose Big Challenges Qingsong Ma Johnny Tian-Zheng Wei Ond rej Bojar Yvette Graham 1 / 31 Overview Overview of Metrics Task Updates to Metric Task in

554 views • 40 slides
TUPA at MRP 2019 A Multi-Task Baseline System CoNLL Shared Task 3 November 2019 1 / 9 Daniel

TUPA at MRP 2019 A Multi-Task Baseline System CoNLL Shared Task 3 November 2019 1 / 9 Daniel

TUPA at MRP 2019 A Multi-Task Baseline System CoNLL Shared Task 3 November 2019 1 / 9 Daniel Hershcovich 1 , Ofjr Arviv 2 1 University of Copenhagen 2 Hebrew University of Jerusalem Transition-Based UCCA Parser look (Hershcovich et al., 2017)

405 views • 12 slides
Shared Task Bilingual Document Alignment Christian Buck and Philipp Koehn University of

Shared Task Bilingual Document Alignment Christian Buck and Philipp Koehn University of

Shared Task Bilingual Document Alignment Christian Buck and Philipp Koehn University of Edinburgh / Johns Hopkins University 12 August 2016 Christian Buck and Philipp Koehn Morphology 12 August 2016 Document Alignment 1 Finding pairs of

426 views • 17 slides
Morphology & Transducers Intro to morphological analysis of languages Motivation for

Morphology & Transducers Intro to morphological analysis of languages Motivation for

Morphology & Transducers Intro to morphological analysis of languages Motivation for morphological analysis in NLP Morphological Recognition by FSAs Transducers Unsupervised Learning (2 nd hour) Speech and Language

744 views • 31 slides
BITCOIN MECHANICS See here: http://www.pptfaq.com /FAQ00125_How_big AND OPTIMIZATIONS

BITCOIN MECHANICS See here: http://www.pptfaq.com /FAQ00125_How_big AND OPTIMIZATIONS

NOTES FOR 1 800x600/bad PROJECTORS: Use at least 22pt* font. *FIXED, Proxima Nova is a bit larger than Arial. BITCOIN MECHANICS See here: http://www.pptfaq.com /FAQ00125_How_big AND OPTIMIZATIONS _should_text_be-_Wh

1.04k views • 56 slides
Stochastic LandauLifshitz Equation on Real Line FARAH El RAFEI School of Mathematics and

Stochastic LandauLifshitz Equation on Real Line FARAH El RAFEI School of Mathematics and

Stochastic LandauLifshitz Equation on Real Line FARAH El RAFEI School of Mathematics and Statistics, UNSW Sydney Joint work with Prof. Beniamin Goldys School of Mathematics and Statistics, The University of Sydney Prof. Thanh Tran School

579 views • 26 slides
The State of Young Adults Balance Sheets: Evidence from the Survey of Consumer Finances Lisa

The State of Young Adults Balance Sheets: Evidence from the Survey of Consumer Finances Lisa

The State of Young Adults Balance Sheets: Evidence from the Survey of Consumer Finances Lisa Dettling and Joanne Hsu Federal Reserve Board May 8, 2014 The analysis and conclusions set forth are those of the authors and do not indicate

517 views • 12 slides
Estimation of Optimally-Combined-Biomarker Accuracy in the Absence of a Gold-Standard Reference

Estimation of Optimally-Combined-Biomarker Accuracy in the Absence of a Gold-Standard Reference

Estimation of Optimally-Combined-Biomarker Accuracy in the Absence of a Gold-Standard Reference Test Estimation of Optimally-Combined-Biomarker Accuracy in the Absence of a Gold-Standard Reference Test L. Garcia Barrado 1 E. Coart 2 T.

516 views • 29 slides
Glass Lantern Slides from Chatsworth Park Elementary Part 2 10/17/2017 Chatsworth Historical

Glass Lantern Slides from Chatsworth Park Elementary Part 2 10/17/2017 Chatsworth Historical

Glass Lantern Slides from Chatsworth Park Elementary Part 2 10/17/2017 Chatsworth Historical Society - Glass Lantern Slides from Chatsworth Park Elementary Part 2 1 Glass Lantern Slides from Chatsworth Park Elementary This presentation

956 views • 79 slides
Bootstrapping Dependency Grammars from Sentence Fragments via Austere Models Valentin I.

Bootstrapping Dependency Grammars from Sentence Fragments via Austere Models Valentin I.

Bootstrapping Dependency Grammars from Sentence Fragments via Austere Models Valentin I. Spitkovsky with Daniel Jurafsky (Stanford University) and Hiyan Alshawi (Google Inc.) Spitkovsky et al. (Stanford & Google) Incomplete Fragments /

1.26k views • 85 slides
The Webinar will begin shortly. You will be hearing the following voices: Frank P. Saladis, PMP

The Webinar will begin shortly. You will be hearing the following voices: Frank P. Saladis, PMP

The Webinar will begin shortly. You will be hearing the following voices: Frank P. Saladis, PMP IPM Day Founder and Webinar Series Organizer Visit www.internationalpmday.org Todays Presenter: Brian Munroe, PMP MTI Learning Visit

843 views • 40 slides
Previous Lecture Todays Lecture Slides for Lecture 30 ENEL 353: Digital Circuits Fall

Previous Lecture Todays Lecture Slides for Lecture 30 ENEL 353: Digital Circuits Fall

ENEL 353 F13 Section 02 Slides for Lecture 30 slide 2/21 ENEL 353 F13 Section 02 Slides for Lecture 30 slide 3/21 Previous Lecture Todays Lecture Slides for Lecture 30 ENEL 353: Digital Circuits Fall 2013 Term Completion of an FSM

299 views • 3 slides

More recommend