Automated Scoring of Picture- based Story Narration Swapna Somasundaran Chong Min Lee Martin Chodorow Xinhao Wang.

Slides:



Advertisements
Similar presentations
Progress Monitoring. Progress Monitoring Steps  Monitor the intervention’s progress as directed by individual student’s RtI plan  Establish a baseline.
Advertisements

Extended Assessments Elementary & Middle/High Reading Oregon Department of Education and Behavioral Research and Teaching January 2007.
Polarity Analysis of Texts using Discourse Structure CIKM 2011 Bas Heerschop Erasmus University Rotterdam Frank Goossen Erasmus.
Language Assessment System (LAS) Links TM Census Test.
® Towards Using Structural Events To Assess Non-Native Speech Lei Chen, Joel Tetreault, Xiaoming Xi Educational Testing Service (ETS) The 5th Workshop.
Copyright © 2014 by Educational Testing Service. All rights reserved. A UTOMATED M EASURES OF S PECIFIC V OCABULARY K NOWLEDGE FROM C ONSTRUCTED R ESPONSES.
Automatic Prosodic Event Detection Using Acoustic, Lexical, and Syntactic Evidence Sankaranarayanan Ananthakrishnan, Shrikanth S. Narayanan IEEE 2007 Min-Hsuan.
Vocal Emotion Recognition with Cochlear Implants Xin Luo, Qian-Jie Fu, John J. Galvin III Presentation By Archie Archibong.
1 Developing Statistic-based and Rule-based Grammar Checkers for Chinese ESL Learners Howard Chen Department of English National Taiwan Normal University.
Development of Automatic Speech Recognition and Synthesis Technologies to Support Chinese Learners of English: The CUHK Experience Helen Meng, Wai-Kit.
Confidential and Proprietary. Copyright © 2010 Educational Testing Service. All rights reserved. Catherine Trapani Educational Testing Service ECOLT: October.
Term 1 Week 9 Syntax.
Prosodic Cues to Discourse Segment Boundaries in Human-Computer Dialogue SIGDial 2004 Gina-Anne Levow April 30, 2004.
Sentiment Lexicon Creation from Lexical Resources BIS 2011 Bas Heerschop Erasmus School of Economics Erasmus University Rotterdam
Extracting Social Meaning Identifying Interactional Style in Spoken Conversation Jurafsky et al ‘09 Presented by Laura Willson.
Improved Tone Modeling for Mandarin Broadcast News Speech Recognition Xin Lei 1, Manhung Siu 2, Mei-Yuh Hwang 1, Mari Ostendorf 1, Tan Lee 3 1 SSLI Lab,
Fall Semester Review English.
ESL Teaching and Reading Strategies
Introduction.  Classification based on function role in classroom instruction  Placement assessment: administered at the beginning of instruction 
The Plot Thickens: Narrative Structure!
Results: Prominence prediction without lexical information Each type of feature reduces the error rate over the baseline. SRF and INF features appear to.
Discovery Education Streaming Overview. Log in Screen.
® Automatic Scoring of Children's Read-Aloud Text Passages and Word Lists Klaus Zechner, John Sabatini and Lei Chen Educational Testing Service.
McEnery, T., Xiao, R. and Y.Tono Corpus-based language studies. Routledge. Unit A 2. Representativeness, balance and sampling (pp13-21)
Measuring Hint Level in Open Cloze Questions Juan Pino, Maxine Eskenazi Language Technologies Institute Carnegie Mellon University International Florida.
Whither Linguistic Interpretation of Acoustic Pronunciation Variation Annika Hämäläinen, Yan Han, Lou Boves & Louis ten Bosch.
Shakespeare Film Project Mr.Wilson’s English Class 506, 406.
2007. Software Engineering Laboratory, School of Computer Science S E Towards Answering Opinion Questions: Separating Facts from Opinions and Identifying.
Copyright 2007, Toshiba Corporation. How (not) to Select Your Voice Corpus: Random Selection vs. Phonologically Balanced Tanya Lambert, Norbert Braunschweiler,
Incident Threading for News Passages (CIKM 09) Speaker: Yi-lin,Hsu Advisor: Dr. Koh, Jia-ling. Date:2010/06/14.
Automatic Detection of Plagiarized Spoken Responses Copyright © 2014 by Educational Testing Service. All rights reserved. Keelan Evanini and Xinhao Wang.
Writing Yearbook. Lesson 1: Notes 01: The NOTES capture and organize the story. – A. A writer uses questions to help focus the story. If a writer has.
Copyright  2014 Pearson Education, Inc. or its affiliate(s). All rights reserved. Automatic Assessment of the Speech of Young English Learners Jian Cheng,
A Bootstrapping Method for Building Subjectivity Lexicons for Languages with Scarce Resources Author: Carmen Banea, Rada Mihalcea, Janyce Wiebe Source:
Copyright © 2015 by Educational Testing Service. 1 Feature Selection for Automated Speech Scoring Anastassia Loukina, Klaus Zechner, Lei Chen, Michael.
14/12/2009ICON Dipankar Das and Sivaji Bandyopadhyay Department of Computer Science & Engineering Jadavpur University, Kolkata , India ICON.
DEVELOPING LISTENING Alejandra Echague C DEVELOPING LISTENING IN A FOREIGN LANGUAGE 1. The foundation skill First to be acquired Mother skill 2.
Enhancing multiple intelligences in story reading.
Predicting Student Emotions in Computer-Human Tutoring Dialogues Diane J. Litman&Kate Forbes-Riley University of Pittsburgh Department of Computer Science.
1 And yeah, it was really good! Positive stance in native and learner speech Sylive De Cock Centre for English Corpus Linguistics Université catholique.
Copyright © 2013 by Educational Testing Service. All rights reserved. 14-June-2013 Detecting Missing Hyphens in Learner Text Aoife Cahill *, Martin Chodorow.
Recognizing Discourse Structure: Speech Discourse & Dialogue CMSC October 11, 2006.
New Acoustic-Phonetic Correlates Sorin Dusan and Larry Rabiner Center for Advanced Information Processing Rutgers University Piscataway,
Ngram models and the Sparcity problem. The task Find a probability distribution for the current word in a text (utterance, etc.), given what the last.
Imposing native speakers’ prosody on non-native speakers’ utterances: Preliminary studies Kyuchul Yoon Spring 2006 NAELL The Division of English Kyungnam.
Creating Subjective and Objective Sentence Classifier from Unannotated Texts Janyce Wiebe and Ellen Riloff Department of Computer Science University of.
Hello, Who is Calling? Can Words Reveal the Social Nature of Conversations?
1 Minimum Error Rate Training in Statistical Machine Translation Franz Josef Och Information Sciences Institute University of Southern California ACL 2003.
Copyright © 2013 by Educational Testing Service. All rights reserved. Evaluating Unsupervised Language Model Adaption Methods for Speaking Assessment ShaSha.
Stages of Test Development By Lily Novita
1 ICASSP Paper Survey Presenter: Chen Yi-Ting. 2 Improved Spoken Document Retrieval With Dynamic Key Term Lexicon and Probabilistic Latent Semantic Analysis.
A Maximum Entropy Language Model Integrating N-grams and Topic Dependencies for Conversational Speech Recognition Sanjeev Khudanpur and Jun Wu Johns Hopkins.
Discourse Analysis of “Keep Smiling” P60 No26 ---By Group 13.
Acoustic Cues to Emotional Speech Julia Hirschberg (joint work with Jennifer Venditti and Jackson Liscombe) Columbia University 26 June 2003.
Topic The common errors in usage of written cohesive devices among secondary school Malaysian learners of English of intermediate proficiency.
Twitter as a Corpus for Sentiment Analysis and Opinion Mining
Cross-Dialectal Data Transferring for Gaussian Mixture Model Training in Arabic Speech Recognition Po-Sen Huang Mark Hasegawa-Johnson University of Illinois.
Predicting Children’s Reading Ability using Evaluator-Informed Features Matthew Black, Joseph Tepperman, Sungbok Lee, and Shrikanth Narayanan Signal Analysis.
Introducing preLAS 2000 Gina Davis Assessment Consultant preLAS.
Language Identification and Part-of-Speech Tagging
Linguistic knowledge for Speech recognition
Dean Luo, Wentao Gu, Ruxin Luo and Lixin Wang
The TOEFL® Junior™ Test
Automatic Fluency Assessment
Anastassia Loukina, Klaus Zechner, James Bruno, Beata Beigman Klebanov
Towards Automatic Fluency Assessment
How do you know when something just doesn’t seem right?
Educational Testing Service (ETS)
Low Level Cues to Emotion
The TOEFL Primary® Speaking Test Tasks
Presentation transcript:

Automated Scoring of Picture- based Story Narration Swapna Somasundaran Chong Min Lee Martin Chodorow Xinhao Wang

Picture-based Story Narration Item in ETS’s TOEFL Junior Comprehensive Test Test for English language skills of non-native middle school students Test elicits stories based on a series of 6 pictures.. Copyright © 2015 by Educational Testing Service. All rights reserved. 2

Picture-based Story Narration Copyright © 2015 by Educational Testing Service. All rights reserved. 3

4 Narrative/ Story Telling Spoken English English Language Responses are scored on a scale from 1 to 4 (best response)

Picture-based Story Narration : Evanini and Wang (2013) [EW13] Fluency – rate of speech, number of words per chunk, average number of pauses, average number of long pauses Pronunciation – normalized Acoustic Model score, average word confidence, average difference in phone duration from native speaker norms Prosody – mean duration between stressed syllables Lexical choice – normalized Language Model score Copyright © 2015 by Educational Testing Service. All rights reserved. 5

Evanini and Wang (2013) Construct coverage Copyright © 2015 by Educational Testing Service. All rights reserved. 6

Extending the Construct coverage Copyright © 2015 by Educational Testing Service. All rights reserved. 7

Features Sets of features corresponding to parts of the construct “Story is full, relevant to the pictures” – Relevance “includes … detail and elaboration” – Detailing – Sentiment “Use of connecting devices helps to link events ….” “Events unfold evenly and the sequence is easy to follow.” – Discourse “word choice” – Collocation Copyright © 2015 by Educational Testing Service. All rights reserved. 8

Features: Relevance Overlap of the content of the response and the content of the pictures Content of the pictures: Manually created reference text corpus (per prompt) – detailed description of each picture [objects/events] – an overall narrative that ties together the events in the pictures Feature: Overlap of the response to the reference corpus Copyright © 2015 by Educational Testing Service. All rights reserved. 9

Features: Detailing Three friends are buying tickets to a movie. Three friends Anna, John and Mary decided to see a movie. Mary buys tickets from the man in a red vest at the counter. Copyright © 2015 by Educational Testing Service. All rights reserved. 10

Features: Detailing Three friends are buying tickets to a movie Three friends Anna, John and Mary decided to see a movie. Mary buys tickets from the man in a red vest at the counter Copyright © 2015 by Educational Testing Service. All rights reserved. - Adjectives and adverbs come into play in the process of detailing. - Assigning names to the characters and places results in a higher number of proper nouns (NNPs). 11

Features: – Presence and counts of Names (NNP) Adjectives Adverbs Copyright © 2015 by Educational Testing Service. All rights reserved. Features: Detailing 12

Features: Sentiment The three friends watched the movie. But Larry could not see as a big man had taken the seat in front of him. The three friends enjoyed the movie. But Larry struggled to see the screen as a big man had taken the seat in front of him. Poor Larry was very sad. Copyright © 2015 by Educational Testing Service. All rights reserved. 13

Features: Sentiment The three friends watched the movie. But Larry could not see as a big man had taken the seat in front of him. The three friends enjoyed the movie. But Larry struggled to see the screen as a big man had taken the seat in front of him. Poor Larry was very sad. Copyright © 2015 by Educational Testing Service. All rights reserved. Subjective language reveals the characters’ private states, emotions and feelings. 14

Resources – Sentiment lexicon developed in previous work in assessments at ETS (Beigman Klebanov et al., 2013) – MPQA subjectivity lexicon (Wilson et al., 2005) Features – Presence and count of polar words from both lexicons – Presence and count of neutral words from MPQA lexicon Copyright © 2015 by Educational Testing Service. All rights reserved. Features: Sentiment 15

Features: Discourse Copyright © 2015 by Educational Testing Service. All rights reserved. When Once After (searching) Soon After (searching) Soon Finally Eventually Finally Eventually Now that As soon as Now that As soon as Buy ticketsFind theater fullSpot some seats Asked to move Settle inMovie starts Unable to see Eat popcornMove 16

Features: Discourse Resource: -Cues from Penn Discourse Treebank -Manually created Discourse Cue lexicon Features: Presence and proportion of cues from the lexicons Presence and proportion of Temporal and Causal cues Score of Temporal and Causal connectives in the response Copyright © 2015 by Educational Testing Service. All rights reserved. 17

Features: Collocation Somasundaran and Chodorow (2014) PMI values for adjacent words (bigrams and trigrams) are obtained over the entire response and are then assigned to bins. Features: – proportion of ngrams falling into each bin – Min, Max and Median PMI values Copyright © 2015 by Educational Testing Service. All rights reserved. 18

Data 3440 responses to 6 prompts scored by human raters (score from 1 to 4) automatic speech recognition (ASR) output Copyright © 2015 by Educational Testing Service. All rights reserved. TOTAL1234 Train Eval QWK between human raters for Train is 0.69 and for Eval is 0.70

Evaluation Random Forest Learner Metric: Quadratic Weighted Kappa Baseline: all features from Evanini and Wang (2013) (EW13) Copyright © 2015 by Educational Testing Service. All rights reserved. 20

Results Copyright © 2015 by Educational Testing Service. All rights reserved. Feature setCVEval Relevance Collocation Discourse Details Subjectivity EW13 baseline All Feats AllFeats+EW

Results Copyright © 2015 by Educational Testing Service. All rights reserved. Feature setCVEval Relevance Collocation Discourse Details Subjectivity EW13 baseline All Feats AllFeats+EW None of the individual feature sets performs better than EW13 baseline 22

Results Copyright © 2015 by Educational Testing Service. All rights reserved. Feature setCVEval Relevance Collocation Discourse Details Subjectivity EW13 baseline All Feats AllFeats+EW All our features combined are better than EW13 baseline, but the differences are not statistically significant. All our features combined are better than EW13 baseline, but the differences are not statistically significant. 23

Results Copyright © 2015 by Educational Testing Service. All rights reserved. Feature setCVEval Relevance Collocation Discourse Details Subjectivity EW13 baseline All Feats AllFeats+EW The best system combines all our features with EW13. Its performance is significantly better than EW13 (p< 0.01). The best system combines all our features with EW13. Its performance is significantly better than EW13 (p< 0.01). 24

Conclusions Explored five linguistic feature types for scoring picture narration We improved the construct coverage of the automated scoring models. Our linguistically motivated features allow for interpretation and explanation of scores. We achieved best performance when combining linguistic and speech-based features. Copyright © 2015 by Educational Testing Service. All rights reserved. 25

Thank You! Swapna Somasundaran – Chong Min Lee – Martin Chodorow – Xinhao Wang – Copyright © 2015 by Educational Testing Service. All rights reserved. 26

Baseline+Feature Copyright © 2015 by Educational Testing Service. All rights reserved. Feature setPerformance EW13 baseline0.48 EW13 + Relevance0.54 EW13 + Collocation0.57 EW13 + Discourse0.49 EW13 + Details0.50 EW13 + Subjectivity

Features: Discourse Copyright © 2015 by Educational Testing Service. All rights reserved. Buy ticketsFind theater fullSpot some seats Request to moveSettled inWatch movie 28