Word Attribute Prediction Enhanced by Lexical Entailment Tasks

Mika Hasegawa, Tetsunori Kobayashi, Yoshihiko Hayashi


Abstract
Human semantic knowledge about concepts acquired through perceptual inputs and daily experiences can be expressed as a bundle of attributes. Unlike the conventional distributed word representations that are purely induced from a text corpus, a semantic attribute is associated with a designated dimension in attribute-based vector representations. Thus, semantic attribute vectors can effectively capture the commonalities and differences among concepts. However, as semantic attributes have been generally created by psychological experimental settings involving human annotators, an automatic method to create or extend such resources is highly demanded in terms of language resource development and maintenance. This study proposes a two-stage neural network architecture, Word2Attr, in which initially acquired attribute representations are then fine-tuned by employing supervised lexical entailment tasks. The quantitative empirical results demonstrated that the fine-tuning was indeed effective in improving the performances of semantic/visual similarity/relatedness evaluation tasks. Although the qualitative analysis confirmed that the proposed method could often discover valid but not-yet human-annotated attributes, they also exposed future issues to be worked: we should refine the inventory of semantic attributes that currently relies on an existing dataset.
Anthology ID:
2020.lrec-1.716
Volume:
Proceedings of the Twelfth Language Resources and Evaluation Conference
Month:
May
Year:
2020
Address:
Marseille, France
Venue:
LREC
SIG:
Publisher:
European Language Resources Association
Note:
Pages:
5846–5854
Language:
English
URL:
https://aclanthology.org/2020.lrec-1.716
DOI:
Bibkey:
Cite (ACL):
Mika Hasegawa, Tetsunori Kobayashi, and Yoshihiko Hayashi. 2020. Word Attribute Prediction Enhanced by Lexical Entailment Tasks. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 5846–5854, Marseille, France. European Language Resources Association.
Cite (Informal):
Word Attribute Prediction Enhanced by Lexical Entailment Tasks (Hasegawa et al., LREC 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.lrec-1.716.pdf