[vc_empty_space][vc_empty_space]
Relation extraction using dependency tree kernel for Bahasa Indonesia
Esperanti D.S.a, Purwarianti A.a
a School of Electronic Engineering and Informatics, Institute Technology Bandung, Bandung, Indonesia
[vc_row][vc_column][vc_row_inner][vc_column_inner][vc_separator css=”.vc_custom_1624529070653{padding-top: 30px !important;padding-bottom: 30px !important;}”][/vc_column_inner][/vc_row_inner][vc_row_inner layout=”boxed”][vc_column_inner width=”3/4″ css=”.vc_custom_1624695412187{border-right-width: 1px !important;border-right-color: #dddddd !important;border-right-style: solid !important;border-radius: 1px !important;}”][vc_empty_space][megatron_heading title=”Abstract” size=”size-sm” text_align=”text-left”][vc_column_text]© 2016 IEEE.Most studies on relation extraction for Bahasa Indonesia were usually done by using string matching method. This approach lacked the syntactical information of the original text data. This paper offers an alternative approach of tree kernel method having advantage of preserving the sentence structure. Each sentence from the text is represented as a dependency parse tree. The tree kernel will calculate the similarity between the trees. Intuitively, the use of dependency structure would yield more accurate result since the related entities would closely connected to each other. Here, we compared our work with bag of word method. In the bag of word method, each pair of possibly related entities within the sentence, the shortest sub sentence containing both entities will be transformed into a feature vector. The similarity between two feature vectors will be calculated using a dot product. The experiments showed that the tree kernel method outperformed the bag of words method. On average, the tree kernel method yielded 77.3% on accuracy while the best bag of words method only had 71.8%. As a trade off, this method runs slower about ∼50x longer than the bag of words method. At the final method, we tried the combined kernel and held the best result with 78.7% accuracy.[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Author keywords” size=”size-sm” text_align=”text-left”][vc_column_text]Combined kernels,Dependency structures,Dependency trees,Feature vectors,Indonesia,Related entities,Relation extraction,Sentence structures[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Indexed keywords” size=”size-sm” text_align=”text-left”][vc_column_text]Bahasa Indonesia,Dependency Tree Kernel,Relation Extraction[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Funding details” size=”size-sm” text_align=”text-left”][vc_column_text][/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”DOI” size=”size-sm” text_align=”text-left”][vc_column_text]https://doi.org/10.1109/ICAICTA.2016.7803105[/vc_column_text][/vc_column_inner][vc_column_inner width=”1/4″][vc_column_text]Widget Plumx[/vc_column_text][/vc_column_inner][/vc_row_inner][/vc_column][/vc_row][vc_row][vc_column][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][/vc_column][/vc_row]