Lexical and morpho-syntactic features in word embeddings a case study of nouns in Swedish
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
We apply real-valued word vectors combined with two different types of classifiers (linear discriminant analysis and feed-forward neural network) to scrutinize whether basic nominal categories can be captured by simple word embedding models. We also provide a linguistic analysis of the errors generated by the classifiers. The targeted language is Swedish, in which we investigate three nominal aspects: uter/neuter, common/proper, and count/mass. They represent respectively grammatical, semantic, and mixed types of nominal classification within languages. Our results show that word embeddings can capture typical grammatical and semantic features such as uter/neuter and common/proper nouns. Nevertheless, the model encounters difficulties to identify classes such as count/mass which not only combine both grammatical and semantic properties, but are also subject to conversion and shift. Hence, we answer the call of the Special Session on Natural Language Processing in Artificial Intelligence by approaching the topic of interfaces between morphology, lexicon, semantics, and syntax via interdisciplinary methods combining machine learning of language and general linguistics.
Original language | English |
---|---|
Title of host publication | ICAART 2018 - Proceedings of the 10th International Conference on Agents and Artificial Intelligence |
Editors | Ana Paula Rocha, Jaap van den Herik |
Number of pages | 12 |
Publisher | SCITEPRESS (Science and Technology Publications, Lda.) |
Publication date | 2018 |
Pages | 663-674 |
ISBN (Electronic) | 9789897582752 |
DOIs | |
Publication status | Published - 2018 |
Event | 10th International Conference on Agents and Artificial Intelligence, ICAART 2018 - Funchal, Madeira, Portugal Duration: 16 Jan 2018 → 18 Jan 2018 |
Conference
Conference | 10th International Conference on Agents and Artificial Intelligence, ICAART 2018 |
---|---|
Land | Portugal |
By | Funchal, Madeira |
Periode | 16/01/2018 → 18/01/2018 |
Sponsor | Institute for Systems and Technologies of Information, Control and Communication (INSTICC) |
Series | ICAART 2018 - Proceedings of the 10th International Conference on Agents and Artificial Intelligence |
---|---|
Volume | 2 |
Bibliographical note
Publisher Copyright:
Copyright © 2018 by SCITEPRESS – Science and Technology Publications, Lda. All rights reserved
- Neural Network, Nominal Classification, Swedish, Word Embedding
Research areas
ID: 366046241