Yonghua Wen

Mr. Yonghua Wen

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
13 January 2023 in Applied Sciences
Verified
Journal Article
Open access
PDF file
WCwei chen
wei chen
YZyihao zhang
yihao zhang
YXYantuan Xian
Yantuan Xian
YWYonghua Wen
Yonghua Wen
Tremendous academic articles face serious information overload problems while supporting literature searches. Finding a research article in a relevant domain that meets researchers’ requirements is challenging. Hence, different paper recommendation models have been proposed to address this issue. However, these models lack a more comprehensive analysis of the connections between the literature, the domain knowledge provided, and the hotspot information expressed in the literature. Previous models make it impossible to locate the appropriate documents for domain literature. Additionally, these models encounter problems such as cold start papers and data sparsity. To overcome these problems, this paper presents a recommendation model termed PRHN. Inputs of the model are the hotspot information network and the domain knowledge graph, which both were developed during the preceding research phase. After the query terms are extracted and the associated heterogeneous literature networks are formed, they are aggregated in a uniform hidden space. Similarity with the candidate set is determined to transform the search problem into a TOP N recommendation problem. Compared to state-of-the-art models, results generated by PRHN on public available datasets show improvement in HR and NDCG. Concretely, results on the metallurgical literature dataset are more conspicuous, with more remarkable improvement in HR and NGCC by approximately 4.5% and 4.2%.

21 March 2023 in Neural Computing and Applications
Verified
Journal Article
Closed access
PDF file
SHShuanghong Huang
Shuanghong Huang
JGJunjun Guo
Junjun Guo
ZYZhengtao Yu
Zhengtao Yu
YWYonghua Wen
Yonghua Wen

9 December 2024 in Applied Sciences
Verified
Journal Article
Open access
PDF file
YWYonghua Wen
Yonghua Wen
YXYantuan Xian
Yantuan Xian
YWYuehan Wang
Yuehan Wang
ZYZhengtao Yu
Zhengtao Yu
Word segmentation is a critical task in natural language processing for southeast Asian Abugida languages, including Thai, Burmese, and Khmer. Existing approaches demonstrate that models using fixed-length windowed context inputs can achieve high segmentation accuracy; however, they often rely on low-level character features or language-specific preprocessing. Character-based methods can limit feature learning, while language-specific features add complexity due to specialized preprocessing requirements. This paper introduces UnifiedCut, which is a neural model that leverages multiple n-grams within a windowed multi-head attention mechanism. This design captures segmentation features from local contexts and multi-perspective n-gram inputs, enhancing generalization and recall, particularly for out-of-vocabulary words. Compared to CNN- and RNN-based approaches, UnifiedCut’s multi-head attention enables finer-grained feature extraction and greater parallelism, resulting in a faster, more scalable solution. Comprehensive experiments on public datasets for Thai, Burmese, and Khmer show that UnifiedCutachieves state-of-the-art performance in word segmentation.

21 May 2023 in Information
Verified
Journal Article
Open access
PDF file
YWYonghua Wen
Yonghua Wen
JGJunjun Guo
Junjun Guo
ZYZhiqiang Yu
Zhiqiang Yu
ZYZhengtao Yu
Zhengtao Yu
Parallel sentences play a crucial role in various NLP tasks, particularly for cross-lingual tasks such as machine translation. However, due to the time-consuming and laborious nature of manual construction, many low-resource languages still suffer from a lack of large-scale parallel data. The objective of pseudo-parallel sentence extraction is to automatically identify sentence pairs in different languages that convey similar meanings. Earlier methods heavily relied on parallel data, which is unsuitable for low-resource scenarios. The current mainstream research direction is to use transfer learning or unsupervised learning based on cross-lingual word embeddings and multilingual pre-trained models; however, these methods are ineffective for languages with substantial differences. To address this issue, we propose a sentence extraction method that leverages image information fusion to extract Chinese–Vietnamese pseudo-parallel sentences from collections of bilingual texts. Our method first employs an adaptive image and text feature fusion strategy to efficiently extract the bilingual parallel sentence pair, and then, a multimodal fusion method is presented to balance the information between the image and text modalities. The experiments on multiple benchmarks show that our method achieves promising results compared to a competitive baseline by infusing additional external image information.

28 May 2024 in Intelligent Data Analysis: An International Journal
Verified
Journal Article
Closed access
PDF file
JXJinlei Xu
Jinlei Xu
YWYonghua Wen
Yonghua Wen
SHShuanghong Huang
Shuanghong Huang
ZYZhengtao Yu
Zhengtao Yu
Most methods for multi-domain adaptive neural machine translation (NMT) currently rely on mixing data from multiple domains in a single model to achieve multi-domain translation. However, this mixing can lead to imbalanced training data, causing the model to focus on training for the large-scale general domain while ignoring the scarce resources of specific domains, resulting in a decrease in translation performance. In this paper, we propose a multi-domain adaptive NMT method based on Domain Data Balancer (DDB) to address the problems of imbalanced data caused by simple fine-tuning. By adding DDB to the Transformer model, we adaptively learn the sampling distribution of each group of training data, replace the maximum likelihood estimation criterion with empirical risk minimization training, and introduce a reward-based iterative update of the bilevel optimizer based on reinforcement learning. Experimental results show that the proposed method improves the baseline model by an average of 1.55 and 0.14 BLEU (Bilingual Evaluation Understudy) scores respectively in English-German and Chinese-English multi-domain NMT.

5 June 2025 in IEEE Transactions on Audio, Speech and Language Processing
Verified
Journal Article
Closed access
ZYZhengtao Yu
Zhengtao Yu
JXJinlei Xu
Jinlei Xu
XHXiang Huang
Xiang Huang
ZDZhongfen Deng
Zhongfen Deng
YWYonghua Wen
Yonghua Wen
PYPhilip S. Yu
Philip S. Yu
Multilingual Neural Machine Translation (NMT) excels in sharing knowledge across languages and transferring insights from high-resource languages to improve performance in low-resource languages. However, its performance lags in specific domains such as legal and medical. Previous works have focused on adding language-specific and domain-specific adapters to achieve domain adaptation. Although effective, these adapter-based methods only use domain data to train additional parameters, limiting the performance of multilingual NMT. In this paper, we propose CDSTX, a novel approach that achieves robust multilingual domain adaptation without relying on adapters, solely leveraging multilingual models. Specifically, we utilize the pretrained model XLM-R and frozen embeddings to preserve its robust multilingual capabilities and design a two-stage training strategy for domain adaptation. This includes separate training for the decoder and fine-tuning of the entire model, ensuring that the model effectively acquires domain knowledge and correctly represents domain-specific text. Moreover, to better utilize the domain information conveyed implicitly by the training data, we devise special domain tokens at the beginning of the source and target sentences called Source&Target Domain Tags. In addition, back translation is employed to enhance the cross-lingual transfer ability of our approach. Our proposed method is evaluated on two datasets across three translation tasks: Single-domain Multilingual NMT, Multi-domain bilingual NMT, and Multilingual Multi-domain NMT. Notably, in the single-domain multilingual NMT task, CDSTX significantly enhances zero-shot domain translation performance, achieving improvements of up to +30 BLEU points through the utilization of back-translation techniques. Even in the bilingual multi-domain NMT task where specific domain data for the target translation direction is unavailable, our method consistently outperforms all SOTA methods. Moreover, in the most challenging Multilingual Multi-domain NMT task, CDSTX surpasses most baseline methods and attains a remarkable gain of +3.0 to +4.6 BLEU points.