Search All site
Search CKIP site

ConceptNet is an ontological system for lexical knowledge and common sense knowledge representation and processing. It is comprised of two major components, namely, a knowledge representation model and knowledge. The knowledge representation model is a frame-based entity-relation model called Extended-HowNet, which provides a universal representational framework for lexical knowledge with meaning composition and decomposition capabilities. The encoded knowledge in ConceptNet includes lexical concepts and common sense knowledge.


In 1988, Dong ZhenDong proposed several important principles for building a knowledge base ( He suggested that all concepts should be defined by a closed set of primitives and features which is different to, organizing concepts into synonym sets, as is the case in WordNet. This approach provides richer information for natural language processing and is more flexible for generating a new concept. Dong used over 2,000 primitives and over 200 hundred Event-role and Features to describe general concepts and map the relations among them. The following is an example.

In 2003, the Sinica CKIP group and Professor Dong began a cooperative project to build a HowNet for traditional Chinese, called HowNet-Big5. We adopted the HowNet-based meaning representation mechanism to define the word meanings of over 90,000 lexical entries in the CKIP Chinese Lexical Knowledge Base. However, we had to make some changes to the HowNet definition structure to address the capabilities of semantic composition and decomposition properties of the model. We invented and added the description of Multi-level meaning representation and complex relation/relations? Instead of using primitives, basic concepts are used as the elements to define complex concepts. As a result, HowNet-Big5 evolved into a new knowledge representation model, called Extended-HowNet. For more details, please read the article " Extended-HowNet: multi-level concept definition and complex relation description" by Chen et al.

The advantages of Extended-HowNet are as follows:

  1. Extended-HowNet represents concepts in more accurate way by not restricting the definition vocabulary to a closed set of primitives only, i.e., any well-defined concepts can be used to define a new concept.

  3. It accords with human cognition models. Since complex concepts are defined by basic concepts, the definitions are easier to understand.
  4. To reach a canonical representation, if a lexical concept is defined by different annotators, the different higher level definitions can be converted into same or similar primitives at the end.

  6. The conversion of primitives into WordNet synsets makes the representation language independent.

  8. The definitions in Extended-HowNet are designed for easy semantic composition, decomposition, and translation into natural language expressions.
  9. Complex definitions are facilitated to define kinship relations, temporal and spatial concepts, comparative notions, etc.

So far we have studied and set specific expressions for comparative constructions, interogative words, and modality in Chinese. In addition, we are working on the dedicate ontological relation. We hope the hierarchical inheritance property of the ontology would help computers understand the relations between concepts. The elaborated illustration on each semantic roles and relations are shown in our E-HowNet Technical Report.

  1. E-HowNet Ontology Online.

  3. Every primitive of HowNet has been connected to the WordNet synsets.

  5. The taxonomy structures for semantic roles have benn constructed. Please see attached files: The semantic roles for Object, The semantics roles for Event, function.

  7. A total of 55,912 words (including 60,482 concepts) in the CKIP Chinese Lexical Knowledge Base have been defined as being the Extended-HowNet format. For example:

  8. More than 80 thousand words in CKIP electronic dictionary (originally contains syntactic information only) are provided with English translations and definitions by Extended-HowNet.

Common sense knowledge is extracted and learned by automatic parsed texts. Word association is the first step of extracting and representing knowledge in ConceptNet. For example, the sentence "We all like butterflies." can be segmented and parsed as follows:

Then three kinds of word-associations are extracted:

The following concept relations are then derived:

experiencer- (we, human, you, John, mother...) like goal- (butterfly, insect, bee, mosquito...),...

The knowledge of lexical concepts and common sense knowledge can then be constructed.


Huang Shu-Ling, Yu-Ming Hsieh, Su-Chu Lin, and Keh-Jiann Chen. 2014. Resolving the Representational Problems of Polarity and Interaction between Process and State Verbs. Computational Linguistics and Chinese Language Processing (IJCLCLP), Vol. 19, No. 2, pp. 33-52.

Shu-Ling Huang, Yu-Ming Hsieh, Su-Chu Lin, and Keh-Jiann Chen. 2013. Lexical Representation and Classification of Eventive Verbs - Polarity and Interaction between Process and State. In Proceedings of the 7th SIGHAN Workshop on Chinese Language Processing (SIGHAN-7).

Su-Chu Lin, Shu-Ling Huang, You-Shan Chung and Keh-Jiann Chen, 2013, The Lexical Knowledge and semantic representation of E-HowNet, Contemporary Linguistics, Vol.15, No.2, pp. 177-194.

Shu-Ling Huang and Keh-Jiann Chen, 2013, Semantic Analysis and Contextual Harmony of Durations, Journal of Chinese Linguistics Vol.41, No.1, pp. 118-144.

You-Shan Chung and Keh-Jiann Chen, 2011, Transitivity of a Chinese Verb-result Compound and Affected Argument of the Result Verb, ROCLING 2011, Taipei, Taiwan.

Wei-Te Chen, Su-Chu Lin, Shu-Ling Huang, You-Shan Chung, and Keh-Jiann Chen, 2010, E-HowNet and Automatic Construction of a Lexical Ontology, the 23rd International Conference on Computational Linguistics, Beijng, China.

You-shan Chung, Keh-Jiann Chen, 2010, Analysis of Chinese Morphemes and Its Application to Sense and Part-Of-Speech Prediction for Chinese Compounds, ICCPOL 2010, California, USA.

Ming-Hong Bai, Jia-Ming You, Keh-Jiann Chen , Jason S. Chang , 2009, Acquiring Translation Equivalences of Multiword Expressions by Normalized Correlation Frequencies, EMNLP 2009, Singapore.

Chia-Hung Tai, Jia-Zen Fan, Shu-Ling Huang, Keh-Jiann Chen, 2009, Automatic Sense Derivation for Determinative-Measure Compounds under the Framework of E-HowNet, CLCLP Vol. 14, #1, March 2009, pp. 19-44 .

Shu-Ling Huang and Keh-Jiann Chen, 2009, A Semantic Analysis of Time Intervals — Core Senses and Relational Senses of a Time Interval, CLSW10, Yantai, China.

Ming-Hong Bai, Keh-Jiann Chen and Jason S. Chang, 2008, Improving Word Alignment by Adjusting Chinese Word Segmentation, Proceedings of IJCNLP2008.

Shu-Ling Huang and Keh-Jiann Chen, 2008, Knowledge Representation and Sense Disambiguation for Interrogatives in E-HowNet, Computational Linguistics and Chinese Language Processing, Vol. 13, No. 3, pp. 255-278.

Chia-hung Tai, Shu-Ling Huang, Keh-Jiann Chen, 2008, A Semantic Composition Method for Deriving Sense Representations of Determinative-Measure Compounds in E-HowNet, Rocling 2008, Taipei, Taiwan.

Shu-Ling Huang, You-Shan Chung, Keh-Jiann Chen. , 2008, E-HowNet: the Expansion of HowNet,, The First National HowNet Workshop, Beijing, China.

Shu-Ling Huang, Yueh-Yin Shih, Keh-Jiann Chen. , 2008, Knowledge Representation for Comparative Constructions in Extended-HowNet,, LANGUAGE AND LINGUISTICS 9.2:395-413.

Shu-Ling Huang, You-Shan Chung, Yueh-Yin Shih, Keh-Jiann Chen, 2007, Knowledge Representation for Interrogatives in E-HowNet, Rocling 2007, Taipei, Taiwan.

You-Shan Chung, Shu-Ling Huang, and Keh-Jiann Chen , 2007, Modality and Modal Sense Representation in E-HowNet, Paclic 21, Seoul, Korea.

Yueh-Yin Shih, Shu-Ling Huang, and Keh-Jiann Chen , 2006, Semantic Representation and Composition for Unknown Compounds in E-HowNet, Paclic 20, Wuhan China.

Shu-Ling Huang, Shih Yueh-Yin, Keh-Jiann Chen, 2006, The Knowledge Representation for Comparison Words in Extended-HowNet, CLSW7, NCTU, Taiwan

Shih Yueh-Yin, Shu-Ling Huang, Yi-Jun Chen , Keh-Jiann Chen, 2005, Semantic representation and composition for spatial concepts in extended-HowNet, IEEE International Conference on Natural Language Processing and Knowledge Engineering, Wuhan, China

Chen Keh-Jiann, Shu-Ling Huang, Yueh-Yin Shih, Yi-Jun Chen, 2005, Extended-HowNet- A Representational Framework for Concepts, OntoLex 2005 - Ontologies and Lexical Resources IJCNLP-05 Workshop, Jeju Island, South Korea

Chen Yi-Jun, Huang Shu-Ling, Shih Yueh-Yin, Chen Keh-Jiann, 2005, The Formulation of Function Word in Extended-HowNet: A Preliminary Study, The 6th Chinese Lexical Semantics Workshop, Xiamen University.

Chen Keh-Jiann, Huang Shu-Ling, Shih Yueh-Yin, Chen Yi-Jun, 2004,.Extended-HowNet: multi-level concept definition and complex relation description, Peking University.

You Jia-Ming, Chen Keh-Jiann, 2004, Automatic Semantic Role Assignment for a Tree Structure, Proceedings of 3rd ACL SIGHAN Workshop, BarcelonaSpain.

You Jia-Ming, Chen Keh-Jiann, 2002, A Study of Word Similarity by Context Vector Models, The 3rd Chinese Lexical Semantics Workshop.


Yueh-Yin  Shih


Yi-Jun Chen, Jia-Ming You, You-Shan Chung, Yueh-Yin Shih, Wei-Teh Chen
Su-Chu Lin, Shu-Ling Huang, Ming-Hong Bai

  Parser    Word Segmentation    Sinica Treebank    Sinica Corpus