VN-KIM IE: Automatic Extraction of Vietnamese Named-Entities on the Web

Nguyen, Truc-Vien T.; Cao, Tru H.

doi:10.1007/s00354-007-0018-4

Cited by 15 publications

(9 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…are respectively vectors over N, C, NC, and I. A feature of a named entity could be unspecified due to the user intention expressed in a query, the incomplete information about that named entity in a document, or the inability of an employed NE recognition engine to fully recognize it [22]. Each of the four component vectors introduced above for a document can be defined as a vector in the traditional tf.idf model on the corresponding space of entity names, classes, name-class pairs, or identifiers, instead of keywords.…”

Section: An Ontology-based Multi-vector Modelmentioning

confidence: 99%

Semantic Search by Latent Ontological Features

Cao

Ngo

2012

New Gener. Comput.

Self Cite

View full text Add to dashboard Cite

Both named entities and keywords are important in defining the content of a text in which they occur. In particular, people often use named entities in information search. However, named entities have ontological features, namely, their aliases, classes, and identifiers, which are hidden from their textual appearance. We propose ontology-based extensions of the traditional Vector Space Model that explore different combinations of those latent ontological features with keywords for text retrieval. Our experiments on benchmark datasets show better search quality of the proposed models as compared to the purely keyword-based model, and their advantages for both text retrieval and representation of documents and queries.The usefulness and explosion of information on the WWW have been challenging research on information retrieval, regarding how that rich and huge resource of information should be exploited efficiently. Information retrieval is not a new area but still attracts much research effort, social and industrial interests, because, on the one hand, it is important for searching required information and, on the other hand, there are still many open problems to be solved to enhance search performance. Retrieval precision and recall could be improved by developing appropriate models, typically as similarity-based, 9, 23) probabilistic relevance, 27) or probabilistic inference 28) ones. Semantic annotation, representation, and processing of documents and queries are another way to obtain better search quality. 6,10,12,29)

show abstract

Section: An Ontology-based Multi-vector Modelmentioning

confidence: 99%

Semantic Search by Latent Ontological Features

Cao

Ngo

2012

New Gener. Comput.

Self Cite

View full text Add to dashboard Cite

show abstract

“…or using gazetteers [8]. Up to now, there are many studies using this method [9], [10] or [11] that obtain high performance including tasks for Vietnamese [2], [3].…”

Section: Related Workmentioning

confidence: 99%

Information Extraction for Vietnamese Real Estate Advertisements

Pham¹,

Pham

2012

2012 Fourth International Conference on Knowledge and Systems Engineering

View full text Add to dashboard Cite

Advertising has appeared in almost all areas of life. The large number of advertisements, especially in real estate domain, has raised a need for an effective way to search and find useful information for users. In this paper, we propose a rule-based approach to build an Information Extraction system for Vietnamese online real estate advertisements. Experimental results shows that our approach is very promising with an overall F-measure of 91% on a collection of data collected from popular Vietnamese real estate websites.

show abstract

“…1. Text example For searching documents based on named entities, a document has to be annotated to identify named entities occurring in them ( [7]). At this stage, an annotation system is used to identify all named entities appearing in the document along with their aliases, class and super-classes.…”

Section: Named Entity Recognitionmentioning

confidence: 99%

Ontology-based proximity search

Le¹,

Cao²,

Hoang

et al. 2011

Proceedings of the 13th International Conference on Information Integration and Web-Based Applications and Services

Self Cite

View full text Add to dashboard Cite

This paper presents our developed general open source for ontology-based information retrieval to answer queries that involve named entities with their ontological features, namely, aliases, classes, and identifiers. We propose a novel approach for semantic search engines that exploit the ontology features of named entities in proximity search and develop an algorithm for computing dynamic distances between named entities and keywords in queries and documents. In particular, it deals with phrase and proximity queries for which the token-based lengths and positions of the queried named entities in a document may vary. The result provides a platform and library for implementing semantic search engines.

show abstract

VN-KIM IE: Automatic Extraction of Vietnamese Named-Entities on the Web

Cited by 15 publications

References 9 publications

Semantic Search by Latent Ontological Features

Semantic Search by Latent Ontological Features

Information Extraction for Vietnamese Real Estate Advertisements

Ontology-based proximity search

Contact Info

Product

Resources

About