Question classification based on co-training style semi-supervised learning

Yu, Zhengtao; Su, Lei; Li, Lina; Zhao, Quan; Mao, Cunli; Guo, Jianyi

doi:10.1016/j.patrec.2010.06.010

Cited by 22 publications

(6 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[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. Zhang [34] and others made full use of the syntax structure of the problem, using the bag-of-words model and the kernel function based on the problem grammar tree to train SVM, and also got a higher classification accuracy.…”

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

“…A_MBWB features and T_MBWB features prove to be very informative for Chinese question classification, and can further boost the question classification accuracy. Table 6 shows the accuracy compared with previous research work for Chinese question classification, including (Wen, 2006), (Sun, 2007), (Zhang, 2009), (Yu, 2010), (Yang, 2013).…”

Section: Comparison With Other Workmentioning

confidence: 99%

“…In Chinese question classification [16][17][18][19][20][21][22][23][24], lexical semantic features and structural features are the guarantees of high performance of question classification. However, due to the fact that the current Chinese NLP technology is not as mature as the English NLP technology, compared with English question classification, it's quite difficult to extract more effect features for Chinese question classification, and as a result, the accuracy of Chinese question classification is much lower than that of English question classification.…”

Section: Introductionmentioning

confidence: 99%

Enriching basic features via multilayer bag‐of‐words binding for Chinese question classification

Yang

Gao

2017

CAAI Transactions on Intelligence Technology

View full text Add to dashboard Cite

Question classification helps to generate more accurate answers in question answering system. For an efficient question classifier, one of the most important tasks is to fully mine useful features. Aiming at solving the problem of lacking of rich syntax and semantic features in Chinese question classification, an operator called MBWB (multilayer bag-of-words binding) is proposed to extract potential features by binding part-of-speech, word sense, named entity and other basic features to bag-of-words, respectively. Through performing MBWB operator on two kinds of bag-ofwords, i.e. A_BOW and T_BOW, the corresponding A_MBWB and T_MBWB features are generated automatically. The MBWB operator can explore potential information contained in basic features, and enrich syntactic and semantic representation of questions. Experimental results on the Chinese question set show that the classification accuracy gets significantly improved when combining two kinds of MBWB features with basic features.

show abstract

“…The answer type taxonomy can be built semi-automatically or by hand, for example, from WordNet (Ray et al 2010;Jochen and Leidner 2004). Many supervised and semi-supervised machine learning algorithm, such as SVMNB, decision tree, co-training, are applied to classifying the questions (Li and Roth 2002;Huang et al 2008;Yu et al 2010;Zhang 2003). The typical features used in a classifier include: the words in the questions, the POS tags of each word and the named entities in the questions.…”

Section: Understanding Of User Queriesmentioning

confidence: 99%

Semantic Analysis-Enhanced Natural Language Interaction in Ubiquitous Learning

Wen

Gao

Yang

2014

Ubiquitous Learning Environments and Technologies

View full text Add to dashboard Cite

Natural language interaction (NLI) is vital and ubiquitous by nature in education environments. It will keep playing key roles in ubiquitous learning and even show stronger presence there. NLI may happen ubiquitously, with many varied forms of texts, bigger textual data, and different learning situations on all kinds of devices, to meet new user needs, thus pose challenges on its design and development. This chapter introduces how natural language processing (NLP) technologies can be employed to help build and improve NLI that can support ubiquitous learning. We emphasize semantic analysis such as semantic role labeling and semantic similarity, and develop and use them to enhance question and answer processing, automated question answering, and automatic text summarization that are involved in our educational systems. Our proposed approaches can improve the technology of natural language processing and help develop different NLI systems in the ubiquitous learning environments and eventually benefit learners.

show abstract

Question classification based on co-training style semi-supervised learning

Cited by 22 publications

References 5 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

Enriching basic features via multilayer bag‐of‐words binding for Chinese question classification

Semantic Analysis-Enhanced Natural Language Interaction in Ubiquitous Learning

Contact Info

Product

Resources

About