Semantic Scholar Open Access 2016 269 sitasi

Analogy-based detection of morphological and semantic relations with word embeddings: what works and what doesn’t.

Anna Rogers Aleksandr Drozd S. Matsuoka

Lihat Sumber DOI

Abstrak

Following up on numerous reports of analogy-based identiﬁcation of “linguistic regularities” in word embeddings, this study applies the widely used vector offset method to 4 types of linguistic relations: inﬂectional and derivational morphology, and lexicographic and en-cyclopedic semantics. We present a balanced test set with 99,200 questions in 40 categories, and we systematically examine how accuracy for different categories is affected by window size and dimensionality of the SVD-based word embeddings. We also show that GloVe and SVD yield similar patterns of results for different categories, offering further evidence for conceptual similarity between count-based and neural-net based models.

Topik & Kata Kunci

Computer Science

Penulis (3)

Anna Rogers

Aleksandr Drozd

S. Matsuoka

Format Sitasi

APA MLA BibTeX

Rogers, A., Drozd, A., Matsuoka, S. (2016). Analogy-based detection of morphological and semantic relations with word embeddings: what works and what doesn’t.. https://doi.org/10.18653/v1/N16-2002

Akses Cepat

Lihat di Sumber doi.org/10.18653/v1/N16-2002

Informasi Jurnal

Tahun Terbit: 2016
Bahasa: en
Total Sitasi: 269×
Sumber Database: Semantic Scholar
DOI: 10.18653/v1/N16-2002
Akses: Open Access ✓