Word classification and hierarchy using co-occurrence word information

Morita, Ken; Atlam, El‐Sayed; Fuketra, Masao; Tsuda, Kazuhiko; Oono, Masaki; Aoe, Jun-ichi

doi:10.1016/j.ipm.2003.08.009

Cited by 25 publications

(10 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Different words seen in the same contexts are good candidates for merging, as are different contexts in which the same words are seen; because appearing in the same context shows that those words can be replaced by each other and assigned to the same cluster as a result. In other words, since the context of a word is the best hint to guess the meaning of that word, we can assume that other words that mutually co-occur with the context of the target word also have similar meaning Morita et al (2004).…”

Section: Term Clustering Algorithmmentioning

confidence: 99%

Bridging the vocabulary gap between questions and answer sentences

Momtazi

Klakow

2015

Information Processing & Management

View full text Add to dashboard Cite

Section: Term Clustering Algorithmmentioning

confidence: 99%

Bridging the vocabulary gap between questions and answer sentences

Momtazi

Klakow

2015

Information Processing & Management

View full text Add to dashboard Cite

“…The concept of the impression vector applied the contrivance of the word vector in the word clustering technique by using the co-occurrence information [11], [12].…”

Section: Generation Of the Impression Vectorsmentioning

confidence: 99%

A Method of Music Retrieval Using Impression Keywords

Morita¹,

Fuketa²,

Aoe³

2015

JSW

Self Cite

View full text Add to dashboard Cite

“…By using the thesaurus the word is classified and hierarchy by the meaning. Here the lexical association is used as the important information to cancel the ambiguous syntax and polysemy [4]. Keyword extraction is the process of extracting the few important words from the given text by considering two assumptions.…”

Section: Rel Ated Workmentioning

confidence: 99%

A context sensitive document indexing approach for Information Retrieval

Vanishree

Sudha

2014

2014 International Conference on Communication and Signal Processing

View full text Add to dashboard Cite

Information retrieval is used to retrieve the information according to the user query. In the existing model the information retrieval is done by analyzing the whole document to answer a query and the terms related to the query are extracted. The indexing weight is applied to all the terms and finally it provides the response to the user. In the existing model they did not take the context into consideration so the information cannot be retrieved efficiently. In this paper, we propose a context-sensitive document indexing approach for information retrieval. The content carrying terms and background terms are separated by using lexical association. Indexing weight is calculated for content carrying terms. The term having the highest indexing weight is considered as the most salient sentence and these sentences are extracted and the document summarization is done. Then according to the user query the information is retrieved, the query is considered as the keyword.Then this keyword is matched with the summarized document. Once the keyword is matched, the particular sentences were extracted by using indexing algorithm. Finally these sentences are provided as the responses for the user. By using this approach, the information retrieval can be done effectively.Index Terms -Content carrying term and background term, sentences splitting, indexing approach, keyword matching.

show abstract

Word classification and hierarchy using co-occurrence word information

Cited by 25 publications

References 7 publications

Bridging the vocabulary gap between questions and answer sentences

Bridging the vocabulary gap between questions and answer sentences

A Method of Music Retrieval Using Impression Keywords

A context sensitive document indexing approach for Information Retrieval

Contact Info

Product

Resources

About