Chinese Question Classification Based on Question Property Kernel

Liu, Li; Yu, Zhengtao; Guo, Jianyi; Mao, Cunli; Hong, Xudong

doi:10.1007/s13042-013-0216-y

Cited by 10 publications

(4 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the basis of this classification system, domestic researchers have formulated a set of Chinese question classification system [31], which has 7 major categories and 60 sub-categories, as shown in Table 2. [32] et al proposed combining part of speech, bag of words and syntactic dependency tree on the basis of SVM, and analyzed the structure of the problem by calculating the value of its kernel function. For the classification of Chinese problems, Yu [33] et al used high-frequency words as features, and trained classifiers on the labeled and unlabeled data sets through a collaborative training algorithm, and achieved 88.9% and 78.2% in the classification of large and small problems respectively.…”

Section: Problem Classificationmentioning

confidence: 99%

A Review of Knowledge Graph-based Question and Answer System Research and Its Application in Chronic Disease Diagnosis

2021

AJCIS

View full text Add to dashboard Cite

Question and answer systems have a long history of development, and with the maturity of knowledge graph technology in recent years, knowledge graph-based question and answer systems are gradually applied to many fields. In this paper, we first discuss the concept of knowledge graph and question and answer system, and then analyze the key technologies used in it. Before dealing with linguistic problems, questions need to be structured and represented by semantic parsing and space vector-based modeling are common approaches. The question and answer system can be divided into three parts: question classification, entity recognition, and relationship extraction, for each of which a large number of techniques have been studied. Finally, a question and answer system based on the knowledge graph of chronic diseases is designed to provide a proven solution for this field, in view of the problem that there are many patients with chronic diseases but lack of sufficient knowledge of the diseases.

show abstract

Section: Problem Classificationmentioning

confidence: 99%

A Review of Knowledge Graph-based Question and Answer System Research and Its Application in Chronic Disease Diagnosis

2021

AJCIS

View full text Add to dashboard Cite

show abstract

“…For example, ME was employed for QC in [35]. Tree kernel SVM [36, 37] and linear kernel SVM [12] have also been used for QC. To take advantage of various classifiers, Li et al [38] proposed a type of semi‐supervised QC method based on ensemble learning, which integrated the bagging algorithm and AdaBoost algorithm.…”

Section: Related Workmentioning

confidence: 99%

“…In machine learning approaches, the performance of QC depends on the features selected and classifier used. Therefore, some researchers have devoted themselves to feature extraction algorithms [7,8] and others have focused on classification algorithms [9][10][11][12]. This paper focuses on a feature extraction algorithm.…”

Section: Introductionmentioning

confidence: 99%

Feature extraction based on information gain and sequential pattern for English question classification

Liu

Chen

et al. 2018

IET softw.

View full text Add to dashboard Cite

The purpose of question classification (QC) is to assign a question to an appropriate category from the set of predefined categories that constitute a question taxonomy. Selected question features are able to significantly improve the performance of QC. However, feature extraction, particularly syntax feature extraction, has a high computational cost. To maintain or enhance performance without syntax features, this study presents a hybrid approach to semantic feature extraction and lexical feature extraction. These features are generated by improved information gain and sequential pattern mining methods, respectively. Selected features are then fed into classifiers for questions classification. Benchmark testing is performed using the public UIUC data set. The results reveal that the proposed approach achieves a coarse accuracy of 96% and fine accuracy of 90.4%, which is superior to existing methods.

show abstract

“…The second is a statistical-based machine learning method, which is based on a certain amount of manually labeled corpus, and often uses methods such as Support Vector Machine (SVM), etc. Liu L [3] et al proposed a kernel function calculation method that combines lexicality and dependency trees to study the problem structure. Thirdly, deep learning based approach, which is different from the traditional manual feature finding approach, which learns the semantic features of the text by self-learning, and the current common approaches are Convolutional Neural Networks (CNN), Recurrent Neural Network (RNN) and its variants, Attention mechanism, and pre-trained language models.…”

Section: Introductionmentioning

confidence: 99%

Research on intention tendency detection for Chinese medical question answering task

Chen

Liu

2023

Third International Conference on Artificial Intelligence and Computer Engineering (ICAICE 2022)

View full text Add to dashboard Cite

In the Chinese medical question and answer task, question intention detection is a very important part. At present, the common intention detection methods mainly use the manually designed matching rules to find the problem features to detect the intention of the problem, but the use of a large amount of labor usually brings about problems such as high cost and poor versatility. A novel method of intention detection is proposed in this paper. First, the collected questions with different intention categories are used to construct intention feature words. Then, based on the BERT pre-training language model, a two-classification model of phrase similarity is constructed. By comparing the combination results of problem word segmentation and the similarity of intention feature words, the multi-classification problem of problem intention detection is transformed into a two-classification problem between multiple phrases. Then we can get the inclination of the question for each intention category, that is the intention category of the question. The experiment shows that the method based on the two-classification model of phrase similarity has better effect than the previous methods, and the F1 value in the test set reaches 90.1.

show abstract

Chinese Question Classification Based on Question Property Kernel

Cited by 10 publications

References 12 publications

A Review of Knowledge Graph-based Question and Answer System Research and Its Application in Chronic Disease Diagnosis

A Review of Knowledge Graph-based Question and Answer System Research and Its Application in Chronic Disease Diagnosis

Feature extraction based on information gain and sequential pattern for English question classification

Research on intention tendency detection for Chinese medical question answering task

Contact Info

Product

Resources

About