Zobrazeno 1 - 10
of 117
pro vyhledávání: '"Harksoo Kim"'
Autor:
Seongsik Park, Harksoo Kim
Publikováno v:
PeerJ Computer Science, Vol 10, p e2311 (2024)
The syntactic information of a dependency tree is an essential feature in relation extraction studies. Traditional dependency-based relation extraction methods can be categorized into hard pruning methods, which aim to remove unnecessary information,
Externí odkaz:
https://doaj.org/article/014da5320fce4dba8f3611e994ac9383
Publikováno v:
ETRI Journal, Vol 46, Iss 1, Pp 7-10 (2024)
Externí odkaz:
https://doaj.org/article/dde9879404264ef6af5c886a4a826c4b
Publikováno v:
Entropy, Vol 25, Iss 3, p 513 (2023)
Text-to-SQL is a task that converts natural language questions into SQL queries. Recent text-to-SQL models employ two decoding methods: sketch-based and generation-based, but each has its own shortcomings. The sketch-based method has limitations in p
Externí odkaz:
https://doaj.org/article/903d3eaf14614024b9cde0b5cb8a924c
Publikováno v:
IEEE Access, Vol 9, Pp 21279-21285 (2021)
Machine reading comprehension (MRC) is a type of question answering mechanism in which a computer reads documents and answers related questions. The accuracies of recent MRC systems surpass those of humans. However, most MRC systems exhibit significa
Externí odkaz:
https://doaj.org/article/c84334147f084669b7a3abbf6d560b96
Publikováno v:
Applied Sciences, Vol 12, Iss 7, p 3367 (2022)
Document-grounded conversation (DGC) is a natural language generation task to generate fluent and informative responses by leveraging dialogue history and document(s). Recently, DGCs have focused on fine-tuning using pretrained language models. Howev
Externí odkaz:
https://doaj.org/article/762de8a1144844c3a12a9403fa546f38
Autor:
Hongjin Kim, Harksoo Kim
Publikováno v:
Applied Sciences, Vol 11, Iss 22, p 10795 (2021)
Named entity recognition (NER) is a natural language processing task to identify spans that mention named entities and to annotate them with predefined named entity classes. Although many NER models based on machine learning have been proposed, their
Externí odkaz:
https://doaj.org/article/d5945ab22afa400fa1c085485e8264e0
Publikováno v:
Entropy, Vol 22, Iss 12, p 1336 (2020)
Previous researchers have considered sentiment analysis as a document classification task, in which input documents are classified into predefined sentiment classes. Although there are sentences in a document that support important evidences for sent
Externí odkaz:
https://doaj.org/article/bc6896314c93476dace194541ff062e0
Autor:
Seongsik Park, Harksoo Kim
Publikováno v:
Applied Sciences, Vol 10, Iss 11, p 3851 (2020)
Relation extraction is a type of information extraction task that recognizes semantic relationships between entities in a sentence. Many previous studies have focused on extracting only one semantic relation between two entities in a single sentence.
Externí odkaz:
https://doaj.org/article/72852ac9a6224752ade1bd214ac8a86f
Autor:
Hongjin Kim, Harksoo Kim
Publikováno v:
Applied Sciences, Vol 10, Iss 11, p 3740 (2020)
In well-spaced Korean sentences, morphological analysis is the first step in natural language processing, in which a Korean sentence is segmented into a sequence of morphemes and the parts of speech of the segmented morphemes are determined. Named en
Externí odkaz:
https://doaj.org/article/aca9adfcc76a4012b9c6289058d029b0
Publikováno v:
Applied Sciences, Vol 10, Iss 9, p 3335 (2020)
A conversation is based on internal knowledge that the participants already know or external knowledge that they have gained during the conversation. A chatbot that communicates with humans by using its internal and external knowledge is called a kno
Externí odkaz:
https://doaj.org/article/bf28c8b8ff17498dbcc517ef6bd4320f