WordGap Automatic Generation of Gap-Filling Vocabulary ...Automatic Generation of Gap-Filling...

22

Transcript of WordGap Automatic Generation of Gap-Filling Vocabulary ...Automatic Generation of Gap-Filling...

Page 1: WordGap Automatic Generation of Gap-Filling Vocabulary ...Automatic Generation of Gap-Filling Vocabulary Exercises for Mobile Learning Susanne Knoop Sabrina Wilske University of Bremen,

WordGap �

Automatic Generation of Gap-Filling

Vocabulary Exercises for Mobile Learning

Susanne KnoopSabrina Wilske

University of Bremen, GermanyDigital Media in Education (Prof. Heidi Schelhowe)

May 22, 2013

Susanne Knoop (University of Bremen) WordGap May 22, 2013 1 / 22

Page 2: WordGap Automatic Generation of Gap-Filling Vocabulary ...Automatic Generation of Gap-Filling Vocabulary Exercises for Mobile Learning Susanne Knoop Sabrina Wilske University of Bremen,

Overview

1 Motivation

2 Previous Work

3 WordGap

4 NLP Tools

5 Outlook

Susanne Knoop (University of Bremen) WordGap May 22, 2013 2 / 22

Page 3: WordGap Automatic Generation of Gap-Filling Vocabulary ...Automatic Generation of Gap-Filling Vocabulary Exercises for Mobile Learning Susanne Knoop Sabrina Wilske University of Bremen,

Obstacles To Language Learning

Susanne Knoop (University of Bremen) WordGap May 22, 2013 3 / 22

Page 4: WordGap Automatic Generation of Gap-Filling Vocabulary ...Automatic Generation of Gap-Filling Vocabulary Exercises for Mobile Learning Susanne Knoop Sabrina Wilske University of Bremen,

The Solution

1 Free CALL software

2 Mobile apps (�learn everywhere, everytime�)

3 Exercises from texts that are of special interest to the user

Susanne Knoop (University of Bremen) WordGap May 22, 2013 4 / 22

Page 5: WordGap Automatic Generation of Gap-Filling Vocabulary ...Automatic Generation of Gap-Filling Vocabulary Exercises for Mobile Learning Susanne Knoop Sabrina Wilske University of Bremen,

Vocabulary Learning With Multiple-Choice Cloze Exercises

� Cloze exercises consist of:

1 A sentence2 A target word that has been replaced by a gap3 (normally three) distractors to distract from the target response

� They are widely used in second language training and testing

Susanne Knoop (University of Bremen) WordGap May 22, 2013 5 / 22

Page 6: WordGap Automatic Generation of Gap-Filling Vocabulary ...Automatic Generation of Gap-Filling Vocabulary Exercises for Mobile Learning Susanne Knoop Sabrina Wilske University of Bremen,

The Challenge

� It normally requires expert knowledge to create cloze exercises:

1 Distractors of multiple-choice cloze exercises should not be totallyunlikely but also not too similar to the target word

2 Distractors should have the same grammatical form as the target word

Susanne Knoop (University of Bremen) WordGap May 22, 2013 6 / 22

Page 7: WordGap Automatic Generation of Gap-Filling Vocabulary ...Automatic Generation of Gap-Filling Vocabulary Exercises for Mobile Learning Susanne Knoop Sabrina Wilske University of Bremen,

Previous Work

� Coniam (1997), Brown et al. (2005): Distractors of the same part ofspeech and similar frequency as the target word

� Sumita et al. (2005): Distractors are false synonyms of the targetword (veri�ed by a Google search)

� Evaluation: Performance of students in the automatically generatedtests correlates strongly with standard vocabulary tests.

Susanne Knoop (University of Bremen) WordGap May 22, 2013 7 / 22

Page 8: WordGap Automatic Generation of Gap-Filling Vocabulary ...Automatic Generation of Gap-Filling Vocabulary Exercises for Mobile Learning Susanne Knoop Sabrina Wilske University of Bremen,

WordGap

� server component and mobile app for Android smartphones

� informal vocabulary learning, adapted to the learner's interest

� multiple-choize cloze exercises from a text �le or webpage

Susanne Knoop (University of Bremen) WordGap May 22, 2013 8 / 22

Page 9: WordGap Automatic Generation of Gap-Filling Vocabulary ...Automatic Generation of Gap-Filling Vocabulary Exercises for Mobile Learning Susanne Knoop Sabrina Wilske University of Bremen,

Share a webpage from the browser

Susanne Knoop (University of Bremen) WordGap May 22, 2013 9 / 22

Page 10: WordGap Automatic Generation of Gap-Filling Vocabulary ...Automatic Generation of Gap-Filling Vocabulary Exercises for Mobile Learning Susanne Knoop Sabrina Wilske University of Bremen,

Send the webpage to WordGap

Susanne Knoop (University of Bremen) WordGap May 22, 2013 10 / 22

Page 11: WordGap Automatic Generation of Gap-Filling Vocabulary ...Automatic Generation of Gap-Filling Vocabulary Exercises for Mobile Learning Susanne Knoop Sabrina Wilske University of Bremen,

Choose a part of speech

Susanne Knoop (University of Bremen) WordGap May 22, 2013 11 / 22

Page 12: WordGap Automatic Generation of Gap-Filling Vocabulary ...Automatic Generation of Gap-Filling Vocabulary Exercises for Mobile Learning Susanne Knoop Sabrina Wilske University of Bremen,

Display the exercise sentence by sentence. . .

Susanne Knoop (University of Bremen) WordGap May 22, 2013 12 / 22

Page 13: WordGap Automatic Generation of Gap-Filling Vocabulary ...Automatic Generation of Gap-Filling Vocabulary Exercises for Mobile Learning Susanne Knoop Sabrina Wilske University of Bremen,

. . . receive immediate feedback. . .

Susanne Knoop (University of Bremen) WordGap May 22, 2013 13 / 22

Page 14: WordGap Automatic Generation of Gap-Filling Vocabulary ...Automatic Generation of Gap-Filling Vocabulary Exercises for Mobile Learning Susanne Knoop Sabrina Wilske University of Bremen,

. . . receive immediate feedback. . .

Susanne Knoop (University of Bremen) WordGap May 22, 2013 14 / 22

Page 15: WordGap Automatic Generation of Gap-Filling Vocabulary ...Automatic Generation of Gap-Filling Vocabulary Exercises for Mobile Learning Susanne Knoop Sabrina Wilske University of Bremen,

. . . get the result.

Susanne Knoop (University of Bremen) WordGap May 22, 2013 15 / 22

Page 16: WordGap Automatic Generation of Gap-Filling Vocabulary ...Automatic Generation of Gap-Filling Vocabulary Exercises for Mobile Learning Susanne Knoop Sabrina Wilske University of Bremen,

The server-client model of WordGap

Susanne Knoop (University of Bremen) WordGap May 22, 2013 16 / 22

Page 17: WordGap Automatic Generation of Gap-Filling Vocabulary ...Automatic Generation of Gap-Filling Vocabulary Exercises for Mobile Learning Susanne Knoop Sabrina Wilske University of Bremen,

The NLP pipeline of the WordGap server

Susanne Knoop (University of Bremen) WordGap May 22, 2013 17 / 22

Page 18: WordGap Automatic Generation of Gap-Filling Vocabulary ...Automatic Generation of Gap-Filling Vocabulary Exercises for Mobile Learning Susanne Knoop Sabrina Wilske University of Bremen,

[plain]

Susanne Knoop (University of Bremen) WordGap May 22, 2013 18 / 22

Page 19: WordGap Automatic Generation of Gap-Filling Vocabulary ...Automatic Generation of Gap-Filling Vocabulary Exercises for Mobile Learning Susanne Knoop Sabrina Wilske University of Bremen,

WordNet

� Hierarchic semantic network of the English language (Miller andFellbaum, 2007)

� WordGap: �nd false synonyms or antonyms of a target word asdistractors

� False synonyms: synonyms of synonyms or words with the samehypernym

� Distractors from the text's context often more suitable than thosefrom WordNet

Susanne Knoop (University of Bremen) WordGap May 22, 2013 19 / 22

Page 20: WordGap Automatic Generation of Gap-Filling Vocabulary ...Automatic Generation of Gap-Filling Vocabulary Exercises for Mobile Learning Susanne Knoop Sabrina Wilske University of Bremen,

Natural Language Tool Kit

� extensive open-source Python library for NLP

� WordGap: sentence and word tokenizing and part of speech tagging

� Naive Bayes Tagger with a cut-o� probability of 0.95

Susanne Knoop (University of Bremen) WordGap May 22, 2013 20 / 22

Page 21: WordGap Automatic Generation of Gap-Filling Vocabulary ...Automatic Generation of Gap-Filling Vocabulary Exercises for Mobile Learning Susanne Knoop Sabrina Wilske University of Bremen,

NodeBox Linguistics

� collection of open-source Python libraries for NLP

� WordGap: generate di�erent grammatical forms to adapt distractorsto the target word

Susanne Knoop (University of Bremen) WordGap May 22, 2013 21 / 22

Page 22: WordGap Automatic Generation of Gap-Filling Vocabulary ...Automatic Generation of Gap-Filling Vocabulary Exercises for Mobile Learning Susanne Knoop Sabrina Wilske University of Bremen,

Outlook

� Include grammatical exercises, e.g. di�erent verb tenses

� Extend to other target languages

Susanne Knoop (University of Bremen) WordGap May 22, 2013 22 / 22