Saved in:
Bibliographic Details
Main Authors: Wei, Chengwei, Pang, Runqi, Kuo, C. -C. Jay
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2401.07475
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911758316208128
author Wei, Chengwei
Pang, Runqi
Kuo, C. -C. Jay
author_facet Wei, Chengwei
Pang, Runqi
Kuo, C. -C. Jay
contents As a fundamental tool for natural language processing (NLP), the part-of-speech (POS) tagger assigns the POS label to each word in a sentence. A novel lightweight POS tagger based on word embeddings is proposed and named GWPT (green word-embedding-based POS tagger) in this work. Following the green learning (GL) methodology, GWPT contains three modules in cascade: 1) representation learning, 2) feature learning, and 3) decision learning modules. The main novelty of GWPT lies in representation learning. It uses non-contextual or contextual word embeddings, partitions embedding dimension indices into low-, medium-, and high-frequency sets, and represents them with different N-grams. It is shown by experimental results that GWPT offers state-of-the-art accuracies with fewer model parameters and significantly lower computational complexity in both training and inference as compared with deep-learning-based methods.
format Preprint
id arxiv_https___arxiv_org_abs_2401_07475
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GWPT: A Green Word-Embedding-based POS Tagger
Wei, Chengwei
Pang, Runqi
Kuo, C. -C. Jay
Computation and Language
As a fundamental tool for natural language processing (NLP), the part-of-speech (POS) tagger assigns the POS label to each word in a sentence. A novel lightweight POS tagger based on word embeddings is proposed and named GWPT (green word-embedding-based POS tagger) in this work. Following the green learning (GL) methodology, GWPT contains three modules in cascade: 1) representation learning, 2) feature learning, and 3) decision learning modules. The main novelty of GWPT lies in representation learning. It uses non-contextual or contextual word embeddings, partitions embedding dimension indices into low-, medium-, and high-frequency sets, and represents them with different N-grams. It is shown by experimental results that GWPT offers state-of-the-art accuracies with fewer model parameters and significantly lower computational complexity in both training and inference as compared with deep-learning-based methods.
title GWPT: A Green Word-Embedding-based POS Tagger
topic Computation and Language
url https://arxiv.org/abs/2401.07475