Wenyan Guo

Dr. Wenyan Guo


Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
10 May 2024 in ACM Transactions on Asian and Low-Resource Language Information Processing
Verified
Journal Article
Open access
WHWenlong Hou
Wenlong Hou
WZWeidong Zhao
Weidong Zhao
XLXianhui Liu
Xianhui Liu
WGWenyan Guo
Wenyan Guo
Named Entity Recognition (NER) in low-resource settings aims to identify and categorize entities in a sentence with limited labeled data. Although prompt-based methods have succeeded in low-resource perspectives, challenges persist in effectively harnessing information and optimizing computational efficiency. In this work, we present a novel prompt-based method to enhance low-resource NER without exhaustive template tuning. First, we construct knowledge-enriched prompts by integrating representative entities and background information to provide informative supervision tailored to each entity type. Then, we introduce an efficient reverse generative framework inspired by question answering (QA), which avoids redundant computations. Finally, we reduce costs by generating entities from their types while retaining model reasoning capacity. Experiment results demonstrate that our method outperforms other baselines on three datasets under few-shot settings.

26 November 2018 in IEEE Access
Verified
Journal Article
Open access
WGWenyan Guo
Wenyan Guo
QZQingtian Zeng
Qingtian Zeng
HDHua Duan
Hua Duan
GYGuiyuan Yuan
Guiyuan Yuan
WNWeijian Ni
Weijian Ni
CLCong Liu
Cong Liu
Emergency plans can be regarded as the effective guidance of hazard emergency responses, and they include the textual descriptions of emergency response processes in terms of natural language. In this paper, we propose an approach to automatically extract emergency response process models from Chinese emergency plans. First, the emergency plan is represented as a text tree according to its layout markups and sentence-sequential relations. Then, process model elements, including four-level response condition formulas, executive roles, response tasks, and flow relations, are identified by rule-based approaches. Finally, an emergency response process tree is generated from both the text tree and extracted process model elements, and is transformed to an emergency response process that is modeled as business process modeling notation. Extensive experiments on real-world emergency plans demonstrate that the proposed approach is capable of extracting emergency response process models that are highly consistent with both the manually extracted models and the textual plans.

7 January 2020 in IEEE Access
Verified
Journal Article
Open access
WGWenyan Guo
Wenyan Guo
QZQingtian Zeng
Qingtian Zeng
HDHua Duan
Hua Duan
WNWeijian Ni
Weijian Ni
TLTong Liu
Tong Liu
NXNengfu Xie
Nengfu Xie
Emergency response plans are regarded as effective guidance for natural disasters and these plans describe emergency response processes in natural language. More specifically, they are textual process descriptions and describe not only how all departments perform their own response tasks, but also how different departments interact with each other. Analyzing text quality of emergency response plans as a typical evaluation approach is an important concern in emergency responses. Because of the flexibility of natural language, emergency response plans normally contain unwanted ambiguities, and it is difficult to check consistency and completeness. Automatic text quality analysis of emergency response plans written in Chinese from the perspective of process descriptions is proposed in this paper. Firstly, three types of response tasks including message sending tasks, message receiving tasks and regular tasks are extracted through Bi-LSTM-CRF networks (a Conditional Random Fields network is combined with a Bidirectional Long Short-Term Memory network). Then, a series of text quality analysis rules associated with extracted response tasks are created. These rules focus on the progressive relationship of four levels of emergency responses, completeness of response tasks, ambiguity and redundancy of emergency response plans. Finally, real-world data is collected to validate the proposed approach, which consists of four types of emergency response plans of natural disasters including district, municipal, provincial and national emergency response plans. It is demonstrated that the proposed approach can be used to facilitate revisions and improvements of emergency response plans.

16 August 2024 in Research Square
Verified
Preprint
Open access
PDF file
WGWenyan Guo
Wenyan Guo
QYQingtao Yang
Qingtao Yang
QZQingtian Zeng
Qingtian Zeng
HDHua Duan
Hua Duan
WNWeijian Ni
Weijian Ni
Emergency response of natural disaster is a complex process involving multiple response levels and cross-organization collaboration. Traditionally, cross-organization collaborative process models of emergency response are constructed based on the common experiences of domain experts and business process modelers. Textual emergency plans are not conducive to emergency performers quickly understanding response tasks and managers analyzing and evaluating the quality of emergency plans of natural disaster. In this paper, a novel approach is proposed to automatically extract cross-organization collaborative process models from emergency plans for supporting emergency response process modeling and the automation analysis of emergency plans. First, an attention mechanism is introduced into the Bi-directional Long Short-Term Memory network combined with a Conditional Random Field (BiLSTM-Attention-CRF), which is trained to identify process elements from sentences. Second, inter-organization relationships are extracted to generate a cross-organization collaborative network of emergency response. Then, response tasks and task relationships are extracted to generate emergency response sub-process models for all organizations. Finally, inter-organization relationships integrate all sub-process models into a global cross-organization collaborative process model of emergency response. A real-world dataset is collected for experimental evaluation and the results illustrate that the proposed approach is capable of extracting automatically cross-organization collaborative process models from emergency plans of natural disaster, and the automatically extracted models are highly consistent with the manually extracted models.

3 November 2024
Verified
Book Chapter
Closed access
PDF file
QZQingtian Zeng
Qingtian Zeng
LZLin Zhang
Lin Zhang
RCRui Cao
Rui Cao
WGWenyan Guo
Wenyan Guo
CLChao Li
Chao Li