Abstract
With the growing amount of unstructured articles
written in natural-language, automated extracting
knowledge of associations between entities is becoming
essential for many applications. In this paper, we develop
automated verb-based algorithm for multiple-relation extraction
from unstructured data obtained on-line. Named
Entity Recognition (NER) techniques were applied to extract
biomedical entities and relations were recognized by algorithms
with Natural Language Processing (NLP) techniques.
Evaluation based on F-measure with random sample of
sentences from biomedical literature results an average
precision of 90% and recall of 82%. We also compared the
performance of proposed algorithm with single-relation extraction
algorithm, indicating improvements of this work. In
conclusion, the preliminary study indicates that this method
for multiple-relation extraction from unstructured literature
is effective. With different training dataset, the algorithm can
be applied to different domains. The automated method can
be applied to detect and predict hidden relationships among
varying areas
written in natural-language, automated extracting
knowledge of associations between entities is becoming
essential for many applications. In this paper, we develop
automated verb-based algorithm for multiple-relation extraction
from unstructured data obtained on-line. Named
Entity Recognition (NER) techniques were applied to extract
biomedical entities and relations were recognized by algorithms
with Natural Language Processing (NLP) techniques.
Evaluation based on F-measure with random sample of
sentences from biomedical literature results an average
precision of 90% and recall of 82%. We also compared the
performance of proposed algorithm with single-relation extraction
algorithm, indicating improvements of this work. In
conclusion, the preliminary study indicates that this method
for multiple-relation extraction from unstructured literature
is effective. With different training dataset, the algorithm can
be applied to different domains. The automated method can
be applied to detect and predict hidden relationships among
varying areas
Original language | English |
---|---|
Title of host publication | Proceddings of the International Conference on Information and Knowledge Engineering |
Publisher | CSREA Press Inc. |
Pages | 115 |
Number of pages | 7 |
ISBN (Print) | 1-60132-463-4 |
Publication status | Published - 2017 |
Keywords
- multiple-relation extraction
- verb-based algorithms
- natural language processing