Automatic Keyword Extraction for Wikification of East Asian Language Documents

Horita, Kensuke; Kimura, Fumihiko; Maeda, Akira

doi:10.7763/ijcte.2016.v8.1015

Cited by 14 publications

(3 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Knowledge graph embedding (KGE) is a method for mapping entities and relations existing in a knowledge graph to the low-dimensional [1], dense space while preserving the ternary's internal structure and allowing for a dispersed representation of things and relations. Similar to tasks in [2][3][4][5], computing the low-dimensional vectors for entities and relations in a knowledge graph enhances recommendation accuracy, Q&A answers, and semantic representations. This improvement is crucial for enhancing the efficacy of knowledge graph applications and is a vital aspect of knowledge graph completion and link prediction.…”

Section: Introductionmentioning

confidence: 99%

Link Prediction Based on Data Augmentation and Metric Learning Knowledge Graph Embedding

Duan,

Han,

Jiang

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

A knowledge graph is a repository that represents a vast amount of information in the form of triplets. In the training process of completing the knowledge graph, the knowledge graph only contains positive examples, which makes reliable link prediction difficult, especially in the setting of complex relations. At the same time, current techniques that rely on distance models encapsulate entities within Euclidean space, limiting their ability to depict nuanced relationships and failing to capture their semantic importance. This research offers a unique strategy based on Gibbs sampling and connection embedding to improve the model’s competency in handling link prediction within complex relationships. Gibbs sampling is initially used to obtain high-quality negative samples. Following that, the triplet entities are mapped onto a hyperplane defined by the connection. This procedure produces complicated relationship embeddings loaded with semantic information. Through metric learning, this process produces complex relationship embeddings imbued with semantic meaning. Finally, the method’s effectiveness is demonstrated on three link prediction benchmark datasets FB15k-237, WN11RR and FB15k.

show abstract

Section: Introductionmentioning

confidence: 99%

Link Prediction Based on Data Augmentation and Metric Learning Knowledge Graph Embedding

Duan,

Han,

Jiang

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…The Top Consecutive Nouns Cohesion (TCNC) method [13] that we used in our previous work is for extracting candidate keyphrases. TCNC connects continuous nouns and treats them as one compound word.…”

Section: Proposed Methodsmentioning

confidence: 99%

A Japanese-Chinese Cross-Language Entity Linking Method with Entity Disambiguation Based on Document Similarity

Song¹,

Zhou²,

Kimura³

et al. 2016

IJKE

Self Cite

View full text Add to dashboard Cite

Abstract-In this paper, we propose a method to automatically discover links between valuable keyphrases in a Japanese document and corresponding Chinese encyclopedia pages. The proposed method has three stages. First, we translate Japanese keyphrases into Chinese using a combination of three translation methods. Second, we extract all Chinese encyclopedia articles of the translated keyphrases. Third, we translate the original Japanese document into Chinese and make a vector of noun frequencies. We calculate the cosine similarities of original articles and all candidate Chinese encyclopedia ones. To find the appropriateness of term description pages for disambiguation, we make a rank with cosine similarity by comparing a Japanese document with Chinese encyclopedia articles. Finally, we add a link from a Japanese keyphrase to top-ranking Chinese encyclopedia article. In this paper, we use Wikipedia and Baidu Baike (an online encyclopedia published by Baidu, a Chinese search engine) articles to conduct our experiment. Although we achieved an accuracy rate of 81% by using Wikipedia, we achieved an accuracy rate of 97% by using Baidu Baike.

show abstract

“…Wang and Zhang (2017) utilized the recurrent neural network method for extracting keywords from reviews of online products. Horita et al(2016) used morphological analysis tools for the extraction of keywords for linking them to related Wikipedia articles. Lahiri et al (2017) used supervised and unsupervised learning methods for extracting keywords from emails to explore the topics in the mails and avoiding excessive information.…”

Section: Introductionmentioning

confidence: 99%

A Comparative Evaluation of Different Keyword Extraction Techniques

Bisht

2021

International Journal of Information Retrieval Research

View full text Add to dashboard Cite

Retrieving keywords in a text is attracting researchers for a long time as it forms a base for many natural language applications like information retrieval, text summarization, document categorization etc. A text is a collection of words that represent the theme of the text naturally and to bring the naturalism under certain rules is itself a challenging task. In the present paper, the authors evaluate different spatial distribution based keyword extraction methods available in the literature on three standard scientific texts. The authors choose the first few high-frequency words for evaluation to reduce the complexity as all the methods are somehow based on frequency. The authors find that the methods are not providing good results particularly in the case of the first few retrieved words. Thus, the authors propose a new measure based on frequency, inverse document frequency, variance, and Tsallis entropy. Evaluation of different methods is done on the basis of precision, recall, and F-measure. Results show that the proposed method provides improved results.

show abstract

Automatic Keyword Extraction for Wikification of East Asian Language Documents

Cited by 14 publications

References 3 publications

Link Prediction Based on Data Augmentation and Metric Learning Knowledge Graph Embedding

Link Prediction Based on Data Augmentation and Metric Learning Knowledge Graph Embedding

A Japanese-Chinese Cross-Language Entity Linking Method with Entity Disambiguation Based on Document Similarity

A Comparative Evaluation of Different Keyword Extraction Techniques

Contact Info

Product

Resources

About