Abstract
Feature norm datasets of human conceptual knowledge, collected in surveys of human volunteers, yield highly interpretable models of word meaning and play an important role in neurolinguistic research on semantic cognition. However, these datasets are limited in size due to practical obstacles associated with exhaustively listing properties for a large number of words. In contrast, the development of distributional modelling techniques and the availability of vast text corpora have allowed researchers to construct effective vector space models of word meaning over large lexicons. However, this comes at the cost of interpretable, human-like information about word meaning. We propose a method for mapping human property knowledge onto a distributional semantic space, which adapts the word2vec architecture to the task of modelling concept features. Our approach gives a measure of concept and feature affinity in a single semantic space, which makes for easy and efficient ranking of candidate human-derived semantic properties for arbitrary words. We compare our model with a previous approach, and show that it performs better on several evaluation tasks. Finally, we discuss how our method could be used to develop efficient sampling techniques to extend existing feature norm datasets in a reliable way.
Original language | English |
---|---|
Title of host publication | Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) |
Publisher | Association for Computational Linguistics |
Pages | 5853-5859 |
Number of pages | 7 |
ISBN (Print) | 9781950737901 |
DOIs | |
Publication status | Published - 2020 |
Event | Conference on Empirical Methods in Natural Language Processing & International Joint Conference on Natural Language Processing (EMNLP-IJCNLP 2019) - Hong Kong, Hong Kong Duration: 03 Nov 2019 → 07 Nov 2019 https://www.emnlp-ijcnlp2019.org/ |
Publication series
Name | EMNLP-IJCNLP 2019 - 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Proceedings of the Conference |
---|
Conference
Conference | Conference on Empirical Methods in Natural Language Processing & International Joint Conference on Natural Language Processing (EMNLP-IJCNLP 2019) |
---|---|
Abbreviated title | EMNLP-IJCNLP 2019 |
Country/Territory | Hong Kong |
City | Hong Kong |
Period | 03/11/2019 → 07/11/2019 |
Internet address |
Keywords
- natural language processing
- semantics
- lexical semantics
ASJC Scopus subject areas
- Computational Theory and Mathematics
- Computer Science Applications
- Information Systems
Fingerprint
Dive into the research topics of 'Feature2vec: Distributional semantic modelling of human property knowledge'. Together they form a unique fingerprint.Student theses
-
Interpretable semantic representations from neural language models and computer vision
Derby, S. (Author), Murphy, B. (Supervisor), Miller, P. (Supervisor) & Devereux, B. (Supervisor), Jul 2022Student thesis: Doctoral Thesis › Doctor of Philosophy
File