API as a social glue

Padhye, Rohan; Mukherjee, Debdoot; Sinha, Vibha Singhal

doi:10.1145/2591062.2591115

Cited by 5 publications

(6 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, the trends and development of information retrieval and mining have transferred from the document-centric to the entity-centric [1]. So knowledge graph which integrates the structural information of concepts across multiple information sources, and links these concepts together [2] is useful for many different domains, such as search result ranking, recommendation, exploratory search, etc [3], [4], [5], [6]. The webpages such as Wikipedia, Quora are potential repositories for building up knowledge graph.…”

Section: Introductionmentioning

confidence: 99%

“…Knowledge Graph is also popularly used in software engineering domain [6], [15], [16], [17] to solve various problems such as software requirements analysis and design [18], coding support, documentation [6], maintenance and testing [19]. But there are few studies focus on structural knowledgebase construction in software engineering domain.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

HDSKG: Harvesting domain specific knowledge graph from content of webpages

Zhao

Xing

Kabir³

et al. 2017

2017 IEEE 24th International Conference on Software Analysis, Evolution and Reengineering (SANER)

View full text Add to dashboard Cite

Knowledge graph is useful for many different domains like search result ranking, recommendation, exploratory search, etc. It integrates structural information of concepts across multiple information sources, and links these concepts together. The extraction of domain specific relation triples (subject, verb phrase, object) is one of the important techniques for domain specific knowledge graph construction. In this research, an automatic method named HDSKG is proposed to discover domain specific concepts and their relation triples from the content of webpages. We incorporate the dependency parser with rule-based method to chunk the relations triple candidates, then we extract advanced features of these candidate relation triples to estimate the domain relevance by a machine learning algorithm. For the evaluation of our method, we apply HDSKG to Stack Overflow (a Q&A website about computer programming). As a result, we construct a knowledge graph of software engineering domain with 35279 relation triples, 44800 concepts, and 9660 unique verb phrases. The experimental results show that both the precision and recall of HDSKG (0.78 and 0.7 respectively) is much higher than the openIE (0.11 and 0.6 respectively). The performance is particularly efficient in the case of complex sentences. Further more, with the self-training technique we used in the classifier, HDSKG can be applied to other domain easily with less training data.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

HDSKG: Harvesting domain specific knowledge graph from content of webpages

Zhao

Xing

Kabir³

et al. 2017

2017 IEEE 24th International Conference on Software Analysis, Evolution and Reengineering (SANER)

View full text Add to dashboard Cite

show abstract

“…The knowledge graph is also widely researched in the software engineering domain. Padhye et al [94] propose a technique to extract the profiles of the usage of API to connect people, projects and libraries in a network. Subramanian et al [95] link source code examples to API documentation by extraction of entity linking.…”

Section: Extract Knowledge Graph In Software Engineering Domainmentioning

confidence: 99%

“…Recently, the trends and development of information retrieval and mining have transferred from the document-centric to the entity-centric [136]. So knowledge graph which integrates the structural information of concepts across multiple information sources, and links these concepts together [160] is useful for many different domains, such as search result ranking, recommendation, exploratory search, etc [80,92,88,94]. The webpages such as Wikipedia, Quora are potential repositories for building up knowledge graph.…”

Section: Background and Motivationmentioning

confidence: 99%

“…Knowledge Graph is also popularly used in software engineering domain [166,167,94,95] to solve various problems such as software requirements analysis and design [168], coding support, documentation [94], maintenance and testing [169]. But there are few studies focus on structural knowledge-base construction in software engineering domain.…”

Section: Background and Motivationmentioning

confidence: 99%

See 1 more Smart Citation

Explainable Q&A system based on domain-specific knowledge graph

Zhao¹

View full text Add to dashboard Cite

Harvest domain specific non-taxonomic relations of ontology from internet by deep neural networks (dnn). BSR winter school Big Software on the Run: Where Software meets Data, p74.The contributions of the co-authors are as follows:• A/Prof. Zhenchang Xing and I proposed the initial idea and designed the study together.• I wrote the manuscript drafts. A/Prof. Zhenchang Xing, A/Prof. Shang-wei Lin and Dr. Muhammad Ashad Kabir revised the manuscript drafts.• I performed all the laboratory work at the School of Computer Science and Engineering and the Nanyang Technological University.• I conducted the evaluation and I mainly analyzed the data. Dr. Jing Li assisted the data analysis.• Dr. Jing Li and Mr. Naoya Sawada assisted the creation of graph database.

show abstract