Semi-Supervised Clustering for Short Answer Scoring

Horbach, Andrea; Pinkal, Manfred

doi:10.17185/duepublico/72289

Tagungsbeitrag 2018 CC BY-NC 4.0

Veröffentlicht

Semi-Supervised Clustering for Short Answer Scoring

This paper investigates the use of semi-supervised clustering for Short Answer Scoring (SAS). In SAS, clustering techniques are an attractive alternative to classification because they provide structured groups of answers in addition to a score. Previous approaches use unsupervised clustering and have teachers label some items after clustering. We propose to re-allocate some of the human annotation effort to before and during the clustering process for (i) feature selection, (ii) for creating pairwise constraints and (iii) for metric learning. Our methods improve clustering performance substantially from 0.504 kappa for unsupervised clustering to 0.566.

Vorschau

Einordnung

Konferenz:: 11th International Conference on Language Resources and Evaluation - LREC 2018; Miyazaki; Japan; 7 - 12 May 2018
Datum der Veröffentlichung:: 2018
URN:: urn:nbn:de:hbz:464-20211130-131339-8
DOI:: 10.17185/duepublico/72289
Sprache:: Englisch
Ressourcentyp:: Text
Schlagwörter:: Short-Answer Scoring; Clustering; Computer-Assisted Language Learning
Kollektion:: E-Publikationen
Sachgruppen der Deutschen Nationalbibliographie:: 004 Informatik
Link URL:: https://aclanthology.org/L18-1641
Einrichtung:: Fakultät für Ingenieurwissenschaften, Informatik und Angewandte Kognitionswissenschaft, Informatik, Sprachtechnologie
Informationen zur Erstveröffentlichung:: Horbach, Andrea/Pinkal, Manfred (2018): Semi-Supervised Clustering for Short Answer Scoring. In: Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), pp. 4065 - 4071. European Language Resources Association. https://aclanthology.org/L18-1641