arXiv Open Access 2015

Good, Better, Best: Choosing Word Embedding Context

James Cross Bing Xiang Bowen Zhou

Lihat Sumber

Abstrak

We propose two methods of learning vector representations of words and phrases that each combine sentence context with structural features extracted from dependency trees. Using several variations of neural network classifier, we show that these combined methods lead to improved performance when used as input features for supervised term-matching.

Topik & Kata Kunci

cs.CL

Penulis (3)

James Cross

Bing Xiang

Bowen Zhou

Format Sitasi

APA MLA BibTeX

Cross, J., Xiang, B., Zhou, B. (2015). Good, Better, Best: Choosing Word Embedding Context. https://arxiv.org/abs/1511.06312

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2015
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓