Semantic Features Based on Word Alignments for Estimating Quality of Text Simplification

Tomoyuki Kajiwara, Atsushi Fujita


Abstract
This paper examines the usefulness of semantic features based on word alignments for estimating the quality of text simplification. Specifically, we introduce seven types of alignment-based features computed on the basis of word embeddings and paraphrase lexicons. Through an empirical experiment using the QATS dataset, we confirm that we can achieve the state-of-the-art performance only with these features.
Anthology ID:
I17-2019
Volume:
Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
Month:
November
Year:
2017
Address:
Taipei, Taiwan
Editors:
Greg Kondrak, Taro Watanabe
Venue:
IJCNLP
SIG:
Publisher:
Asian Federation of Natural Language Processing
Note:
Pages:
109–115
Language:
URL:
https://aclanthology.org/I17-2019
DOI:
Bibkey:
Cite (ACL):
Tomoyuki Kajiwara and Atsushi Fujita. 2017. Semantic Features Based on Word Alignments for Estimating Quality of Text Simplification. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 109–115, Taipei, Taiwan. Asian Federation of Natural Language Processing.
Cite (Informal):
Semantic Features Based on Word Alignments for Estimating Quality of Text Simplification (Kajiwara & Fujita, IJCNLP 2017)
Copy Citation:
PDF:
https://aclanthology.org/I17-2019.pdf