A4 Refereed article in a conference publication

Towards Automatic Short Answer Assessment for Finnish as a Paraphrase Retrieval Task




AuthorsChang Li-Hsin, Kanerva Jenna, Ginter Filip

EditorsEkaterina Kochmar, Jill Burstein, Andrea Horbach, Ronja Laarmann-Quante, Nitin Madnani, Anaïs Tack, Victoria Yaneva, Zheng Yuan, Torsten Zesch

Conference nameWorkshop on Innovative Use of NLP for Building Educational Applications

PublisherAssociation for Computational Linguistics (ACL)

Publication year2022

Book title Proceedings of the 17th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2022)

Journal name in sourceBEA 2022 - 17th Workshop on Innovative Use of NLP for Building Educational Applications, Proceedings

First page 262

Last page271

ISBN978-1-955917-83-4

DOIhttps://doi.org/10.18653/v1/2022.bea-1.30(external)

Web address https://aclanthology.org/2022.bea-1.30/(external)

Self-archived copy’s web addresshttps://research.utu.fi/converis/portal/detail/Publication/176823390(external)


Abstract

Automatic grouping of textual answers has the potential of allowing batch grading, but is challenging because the answers, especially longer essays, have many claims. To explore the feasibility of grouping together answers based on their semantic meaning, this paper investigates the grouping of short textual answers, proxies of single claims. This is approached as a paraphrase identification task, where neural and non-neural sentence embeddings and a paraphrase identification model are tested. These methods are evaluated on a dataset consisting of over 4000 short textual answers from various disciplines. The results map out the suitable question types for the paraphrase identification model and those for the neural and non-neural methods.


Downloadable publication

This is an electronic reprint of the original article.
This reprint may differ from the original in pagination and typographic detail. Please cite the original version.





Last updated on 2024-26-11 at 18:49