-
Chapter and Conference Paper
A Framework for Dictionary Development: Building Domain Dictionary for Legal Field
The domain dictionary is a hotspot of research in natural language processing. Constructing a dictionary effectively for a specific field enables more precise labeling and classification of words. The developm...
-
Chapter and Conference Paper
Deps-SAN: Neural Machine Translation with Dependency-Scaled Self-Attention Network
Syntax knowledge contributes its powerful strength in Neural machine translation (NMT) tasks. Early NMT works supposed that syntax details can be automatically learned from numerous texts via attention network...
-
Chapter and Conference Paper
Simplifying Aspect-Sentiment Quadruple Prediction with Cartesian Product Operation
Aspect sentiment quad prediction (ASQP) is an emerging subtask of aspect-based sentiment analysis, which seeks to predict the sentiment quadruplets of aspect terms, aspect categories, associated sentiment pola...
-
Chapter and Conference Paper
Towards Malay Abbreviation Disambiguation: Corpus and Unsupervised Model
Abbreviation disambiguation constitutes a highly crucial natural language processing task in all languages, including Malay. Its objective involves the identification of the most suitable definition, from a ca...
-
Chapter and Conference Paper
Towards Indonesian Phrase Extraction: Framework and Corpus
Mining quality phrases is one of the basic tasks of natural language processing. Current research mainly focuses on universal languages but is rarely conducted for low-resource languages such as Indonesian. To...
-
Chapter and Conference Paper
A Fine-Grained Social Bias Measurement Framework for Open-Domain Dialogue Systems
A pre-trained model based on a large-scale corpus can effectively improve the performance of open-domain dialogue systems in terms of performance. However, recent studies have shown various ethical issues in p...
-
Chapter and Conference Paper
Construction and Evaluation of Chinese Word Segmentation Datasets in Malay Archipelago
In recent years, there has been numerous mature research on Chinese word segmentation (CWS). However, the existing research mainly focuses on mainland Mandarin word segmentation, and the research on CWS of oth...
-
Chapter and Conference Paper
Multilingual China-Related News Identification Framework Based on Multiple Strategies
In order to overcome the high recall but low accuracy of China-related news identification methods based on dictionary or machine learning, a China-related news identification framework for multilingual news i...
-
Chapter and Conference Paper
Pre-trained Language Models for Tagalog with Multi-source Data
Pre-trained language models (PLMs) for Tagalog can be categorized into two kinds: monolingual models and multilingual models. However, existing monolingual models are only trained in small-scale Wikipedia corp...
-
Chapter and Conference Paper
Pre-trained Models and Evaluation Data for the Myanmar Language
Pre-trained language models (PLMs), which working for downstream natural language processing (NLP) tasks with the large corpus ubiquitously and favorably, have outstanding effectiveness due to their ability to...
-
Chapter and Conference Paper
An Indonesian Sentiment Classification Model Based on Multi-task Learning
With the rapid development of social network, people are keen on giving voice to their feelings on social media containing their attitude towards products or services, which is significant for company to have ...
-
Chapter and Conference Paper
Research on Pseudo-label Technology for Multi-label News Classification
Multi-label news classification exerts a significant importance with the growing size of news containing multiple semantics. However, most of the existing multi-label classification methods rely on large-scale...
-
Chapter and Conference Paper
Multi-domain Sentiment Classification on Self-constructed Indonesian Dataset
Domain-dependence limits the application of a well-trained sentiment classifier based on one domain data in other different domains. To solve this problem, multi-domain sentiment classification has received gr...
-
Chapter and Conference Paper
A Framework for Identifying Event’s Relevance Comments in Twitter
Nowadays, with the continuous development of the Internet, public opinion analysis has become an indispensable means for governments and companies to grasp public opinion trends and respond promptly to emergen...
