Please use this identifier to cite or link to this item:

Title: Supervised word sense disambiguation on polysemy with bidirectional LSTM
Authors: 劉吉軒
Jyi-Shane Liu
Lai, Huei-Ling
Hsu, Hsiao-Ling
Lin, Chia-Hung
Chen, Yanhong
Contributors: 資科系
Keywords: Word sense disambiguation;POSTaiwan Hakka;low-resource language;neural network models
Date: 2020-05
Issue Date: 2021-06-04 14:50:30 (UTC+8)
Abstract: While word sense disambiguation (WSD) has been extensively studied in natural language processing, such a task in low-resource languages still receives little attention. Findings based on a few dominant languages may lead to narrow applications. A language-specific WSD system is in need to implement in low-resource languages, for instance, in Taiwan Hakka. This study examines the performance of DNN and Bi-LSTM in WSD tasks on polysemous BUNin Taiwan Hakka. Both models are trained and tested on a small amount of hand-crafted labeled data. Two experiments are designed with four kinds of input features and two window spans to explore what information is needed for the models to achieve their best performance. The results show that to achieve the best performance, DNN and Bi-LSTM models prefer different kinds of input features and window spans.
Relation: The 21st Chinese Lexical Semantics Workshop (CLSW2020), City University of Hong Kong
Data Type: conference
DOI 連結:
Appears in Collections:[資訊科學系] 會議論文

Files in This Item:

File Description SizeFormat
569.pdf187KbAdobe PDF12View/Open

All items in 學術集成 are protected by copyright, with all rights reserved.

社群 sharing