Word attribute prediction enhanced by lexical entailment tasks

研究成果: Conference contribution

抄録

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.

本文言語English
ホスト出版物のタイトルLREC 2020 - 12th International Conference on Language Resources and Evaluation, Conference Proceedings
編集者Nicoletta Calzolari, Frederic Bechet, Philippe Blache, Khalid Choukri, Christopher Cieri, Thierry Declerck, Sara Goggi, Hitoshi Isahara, Bente Maegaard, Joseph Mariani, Helene Mazo, Asuncion Moreno, Jan Odijk, Stelios Piperidis
出版社European Language Resources Association (ELRA)
ページ5846-5854
ページ数9
ISBN(電子版)9791095546344
出版ステータスPublished - 2020
イベント12th International Conference on Language Resources and Evaluation, LREC 2020 - Marseille, France
継続期間: 2020 5 112020 5 16

出版物シリーズ

名前LREC 2020 - 12th International Conference on Language Resources and Evaluation, Conference Proceedings

Conference

Conference12th International Conference on Language Resources and Evaluation, LREC 2020
CountryFrance
CityMarseille
Period20/5/1120/5/16

ASJC Scopus subject areas

  • Language and Linguistics
  • Education
  • Library and Information Sciences
  • Linguistics and Language

フィンガープリント 「Word attribute prediction enhanced by lexical entailment tasks」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル