Xiaobing Zhao

Xiaobing Zhao

Auto-generated profile, based on publicly available information

Xiaobing Zhao

Minzu University of China, Beijing, China

Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

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

Representative Publications

View All Publications
26 November 2019 in IEEE Access
Verified
Journal Article
Open access
YSYuan Sun
Yuan Sun
LWLike Wang
Like Wang
CCChaofan Chen
Chaofan Chen
TXTianci Xia
Tianci Xia
XZXiaobing Zhao
Xiaobing Zhao
The task of relation extraction is classifying the relations between two entities in a sentence. Distant supervision relation extraction can automatically align entities in texts based on Knowledge Base without labeled training data. For low-resource language relation extraction, such as Tibetan, the main problem is the lack of labeled training data. In this paper, we propose an improved distant supervised relation extraction model based on Piecewise Convolutional Neural Network (PCNN) to expand the Tibetan corpus. We add self-attention mechanism and soft-label method to decrease wrong labels, and use Embeddings from Language Models (ELMo) to solve the semantic ambiguity problem. Meanwhile, according to the Tibetan characteristics, we combine the word vector and part of speech vector to extract deeply feature of words. Finally, the experimental results show that P@avg value increases by 14.4% than baseline.

27 December 2023
Verified
Conference Paper
Open access
YSYingli Shen
Yingli Shen
XZXiaobing Zhao
Xiaobing Zhao
Reinforcement learning (RL) is a powerful technique for learning from data and feedback, but its effective application to natural language processing (NLP) tasks remains an open question. Consequently, this paper first introduces the general concepts of RL and the common approaches. Subsequently, we review the task construction settings and the application of RL for various NLP problems, such as machine translation, dialogue system, and text generation. Finally, we discuss some promising research directions and challenges of RL in NLP. We hope that our work can provide a comprehensive overview and inspire more research on this promising yet challenging topic.

1 January 2017
Verified
Conference Paper
Closed access
LMLujia Ma
Lujia Ma
WBWei Bao
Wei Bao
WBWugedele Bao
Wugedele Bao
WYWuriga Yuan
Wuriga Yuan
THTao Huang
Tao Huang
XZXiaobing Zhao
Xiaobing Zhao
A Mongolian Information Retrieval System based on Solr is proposed in this paper. The system implements the retrieval of Mongolian data store in our local machine. Firstly, in this paper, we built a Mongolian corpus with one million words, which has been corrected manually. Secondly, after being transcoded, theses data was represented by Latin characters. Finally, we used Solr to build indexes and documents so that we do queries on millions of data within seconds.

1 November 2012
Verified
Conference Paper
Closed access
LQLirong Qiu
Lirong Qiu
CLCongjun Long
Congjun Long
XZXiaobing Zhao
Xiaobing Zhao
Syntactic parsing and semantic role labeling have been studied in natural language processing for many years and many good research results have been obtained. According to the characteristics of Tibetan, a joint approach for syntactic parsing and semantic role labeling is proposed in this paper. This approach, based on the theory of syntax and semantic features on Tibetan verbs, and with the predicate chunk patterns, is used to label corpus for the study of Tibetan language processing.

10 February 2025 in ACM Transactions on Asian and Low-Resource Language Information Processing
Verified
Journal Article
Open access
CTChao Tang
Chao Tang
ZTZelin Tan
Zelin Tan
XZXiaobing Zhao
Xiaobing Zhao
With the advancement of pre-trained language models, prompt learning has emerged as a trend for text classification. It offers several advantages over traditional machine learning methods, particularly for low-resource natural language processing tasks. Prompt learning enables fine-tuning of pre-trained language models on relatively small datasets, eliminating the need for a large number of expensive labeled samples. This article proposes an effective approach that combines prompt learning and ensemble learning, aiming to enhance the performance of individual language models in Tibetan text classification tasks. This approach introduces a different perspective by transforming the traditional text classification problem into an entailment relationship exploration. Instead of directly assigning categories to sentences, models judge the sentence category based on whether it is entailed by a given prompt. This innovative method enables us to leverage the strengths of prompt learning and ensemble learning simultaneously, resulting in improved classification accuracy. To evaluate the effectiveness of our approach, we conducted extensive experiments on two public datasets, TNCC and WCM. The experimental results demonstrate the effectiveness of our method, achieving weighted F1 scores of 72.72% and 78% on TNCC and WCM, respectively. Compared to traditional machine learning methods, this prompt learning approach exhibits a significant 10% performance gain in low-resource natural language processing tasks.