SOFTCARDINALITY: Hierarchical text overlap for student response analysis

Sergio Jimenez, Claudia Becerra, Alexander Gelbukh

Research output: Contribution to conferencePaper

13 Citations (Scopus)

Abstract

c 2013 Association for Computational Linguistics In this paper we describe our system used to participate in the Student-Response-Analysis task-7 at SemEval 2013. This system is based on text overlap through the soft cardinality and a new mechanism for weight propagation. Although there are several official performance measures, taking into account the overall accuracy throughout the two availabe data sets (Beetle and SciEntsBank), our system ranked first in the 2 way classification task and second in the others. Furthermore, our system performs particularly well with “unseen-domains” instances, which was the more challenging test set. This paper also describes another system that integrates this method with the lexical-overlap baseline provided by the task organizers obtaining better results than the best official results. We concluded that the soft cardinality method is a very competitive baseline for the automatic evaluation of student responses.
Original languageAmerican English
Pages280-284
Number of pages251
StatePublished - 1 Jan 2013
Event*SEM 2013 - 2nd Joint Conference on Lexical and Computational Semantics -
Duration: 1 Jan 2013 → …

Conference

Conference*SEM 2013 - 2nd Joint Conference on Lexical and Computational Semantics
Period1/01/13 → …

Fingerprint

response analysis
student
Computational linguistics
Students
beetle
method
test
evaluation

Cite this

Jimenez, S., Becerra, C., & Gelbukh, A. (2013). SOFTCARDINALITY: Hierarchical text overlap for student response analysis. 280-284. Paper presented at *SEM 2013 - 2nd Joint Conference on Lexical and Computational Semantics, .
Jimenez, Sergio ; Becerra, Claudia ; Gelbukh, Alexander. / SOFTCARDINALITY: Hierarchical text overlap for student response analysis. Paper presented at *SEM 2013 - 2nd Joint Conference on Lexical and Computational Semantics, .251 p.
@conference{61a299f1493e4e49be46d19743172e02,
title = "SOFTCARDINALITY: Hierarchical text overlap for student response analysis",
abstract = "c 2013 Association for Computational Linguistics In this paper we describe our system used to participate in the Student-Response-Analysis task-7 at SemEval 2013. This system is based on text overlap through the soft cardinality and a new mechanism for weight propagation. Although there are several official performance measures, taking into account the overall accuracy throughout the two availabe data sets (Beetle and SciEntsBank), our system ranked first in the 2 way classification task and second in the others. Furthermore, our system performs particularly well with “unseen-domains” instances, which was the more challenging test set. This paper also describes another system that integrates this method with the lexical-overlap baseline provided by the task organizers obtaining better results than the best official results. We concluded that the soft cardinality method is a very competitive baseline for the automatic evaluation of student responses.",
author = "Sergio Jimenez and Claudia Becerra and Alexander Gelbukh",
year = "2013",
month = "1",
day = "1",
language = "American English",
pages = "280--284",
note = "*SEM 2013 - 2nd Joint Conference on Lexical and Computational Semantics ; Conference date: 01-01-2013",

}

Jimenez, S, Becerra, C & Gelbukh, A 2013, 'SOFTCARDINALITY: Hierarchical text overlap for student response analysis', Paper presented at *SEM 2013 - 2nd Joint Conference on Lexical and Computational Semantics, 1/01/13 pp. 280-284.

SOFTCARDINALITY: Hierarchical text overlap for student response analysis. / Jimenez, Sergio; Becerra, Claudia; Gelbukh, Alexander.

2013. 280-284 Paper presented at *SEM 2013 - 2nd Joint Conference on Lexical and Computational Semantics, .

Research output: Contribution to conferencePaper

TY - CONF

T1 - SOFTCARDINALITY: Hierarchical text overlap for student response analysis

AU - Jimenez, Sergio

AU - Becerra, Claudia

AU - Gelbukh, Alexander

PY - 2013/1/1

Y1 - 2013/1/1

N2 - c 2013 Association for Computational Linguistics In this paper we describe our system used to participate in the Student-Response-Analysis task-7 at SemEval 2013. This system is based on text overlap through the soft cardinality and a new mechanism for weight propagation. Although there are several official performance measures, taking into account the overall accuracy throughout the two availabe data sets (Beetle and SciEntsBank), our system ranked first in the 2 way classification task and second in the others. Furthermore, our system performs particularly well with “unseen-domains” instances, which was the more challenging test set. This paper also describes another system that integrates this method with the lexical-overlap baseline provided by the task organizers obtaining better results than the best official results. We concluded that the soft cardinality method is a very competitive baseline for the automatic evaluation of student responses.

AB - c 2013 Association for Computational Linguistics In this paper we describe our system used to participate in the Student-Response-Analysis task-7 at SemEval 2013. This system is based on text overlap through the soft cardinality and a new mechanism for weight propagation. Although there are several official performance measures, taking into account the overall accuracy throughout the two availabe data sets (Beetle and SciEntsBank), our system ranked first in the 2 way classification task and second in the others. Furthermore, our system performs particularly well with “unseen-domains” instances, which was the more challenging test set. This paper also describes another system that integrates this method with the lexical-overlap baseline provided by the task organizers obtaining better results than the best official results. We concluded that the soft cardinality method is a very competitive baseline for the automatic evaluation of student responses.

UR - https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84994114125&origin=inward

UR - https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=84994114125&origin=inward

M3 - Paper

SP - 280

EP - 284

ER -

Jimenez S, Becerra C, Gelbukh A. SOFTCARDINALITY: Hierarchical text overlap for student response analysis. 2013. Paper presented at *SEM 2013 - 2nd Joint Conference on Lexical and Computational Semantics, .