Details
| Original language | English |
|---|---|
| Title of host publication | 2021 IEEE International Conference on Big Knowledge |
| Subtitle of host publication | (ICBK) |
| Editors | Zhiguo Gong, Xue Li, Sule Gunduz Oguducu, Lei Chen, Baltasar Fernandez Manjon, Xindong Wu |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 315-322 |
| Number of pages | 8 |
| ISBN (electronic) | 9781665438582 |
| Publication status | Published - 2021 |
| Event | 12th IEEE International Conference on Big Knowledge, ICBK 2021 - Virtual, Auckland, New Zealand Duration: 7 Dec 2021 → 8 Dec 2021 |
Abstract
Decision-making tasks usually follow five steps: identifying the problem, collecting data, extracting evidence, iden-tifying arguments, and making the decision. This paper focuses on two steps of decision-making: extracting evidence by building knowledge graphs (KGs) of specialized topics and identifying sentences' arguments through sentence-level argument mining. We present a hybrid model that combines topic modeling using latent Dirichlet allocation (LDA) and word embeddings to obtain external knowledge from structured and unstructured data. We use a topic model to extract topic- and sentence-specific evidence from the structured knowledge base Wikidata. A knowledge graph is constructed based on the cosine similarity between the entity word vectors of Wikidata and the vector of the given sentence. A second graph based on topic-specific articles found via Google supplements the general incompleteness of the structured knowledge base. Combining these graphs, we obtain a graph-based model that, as our evaluation shows, successfully capitalizes on both structured and unstructured data.
Keywords
- Argument mining, Knowledge graph, Topic model
ASJC Scopus subject areas
- Computer Science(all)
- Artificial Intelligence
- Computer Science(all)
- Computer Science Applications
- Computer Science(all)
- Information Systems
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
2021 IEEE International Conference on Big Knowledge: (ICBK). ed. / Zhiguo Gong; Xue Li; Sule Gunduz Oguducu; Lei Chen; Baltasar Fernandez Manjon; Xindong Wu. Institute of Electrical and Electronics Engineers Inc., 2021. p. 315-322.
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Topic-Guided Knowledge Graph Construction for Argument Mining
AU - Li, Weichen
AU - Abels, Patrick
AU - Ahmadi, Zahra
AU - Burkhardt, Sophie
AU - Schiller, Benjamin
AU - Gurevych, Iryna
AU - Kramer, Stefan
PY - 2021
Y1 - 2021
N2 - Decision-making tasks usually follow five steps: identifying the problem, collecting data, extracting evidence, iden-tifying arguments, and making the decision. This paper focuses on two steps of decision-making: extracting evidence by building knowledge graphs (KGs) of specialized topics and identifying sentences' arguments through sentence-level argument mining. We present a hybrid model that combines topic modeling using latent Dirichlet allocation (LDA) and word embeddings to obtain external knowledge from structured and unstructured data. We use a topic model to extract topic- and sentence-specific evidence from the structured knowledge base Wikidata. A knowledge graph is constructed based on the cosine similarity between the entity word vectors of Wikidata and the vector of the given sentence. A second graph based on topic-specific articles found via Google supplements the general incompleteness of the structured knowledge base. Combining these graphs, we obtain a graph-based model that, as our evaluation shows, successfully capitalizes on both structured and unstructured data.
AB - Decision-making tasks usually follow five steps: identifying the problem, collecting data, extracting evidence, iden-tifying arguments, and making the decision. This paper focuses on two steps of decision-making: extracting evidence by building knowledge graphs (KGs) of specialized topics and identifying sentences' arguments through sentence-level argument mining. We present a hybrid model that combines topic modeling using latent Dirichlet allocation (LDA) and word embeddings to obtain external knowledge from structured and unstructured data. We use a topic model to extract topic- and sentence-specific evidence from the structured knowledge base Wikidata. A knowledge graph is constructed based on the cosine similarity between the entity word vectors of Wikidata and the vector of the given sentence. A second graph based on topic-specific articles found via Google supplements the general incompleteness of the structured knowledge base. Combining these graphs, we obtain a graph-based model that, as our evaluation shows, successfully capitalizes on both structured and unstructured data.
KW - Argument mining
KW - Knowledge graph
KW - Topic model
UR - http://www.scopus.com/inward/record.url?scp=85125065684&partnerID=8YFLogxK
U2 - 10.1109/ICKG52313.2021.00049
DO - 10.1109/ICKG52313.2021.00049
M3 - Conference contribution
AN - SCOPUS:85125065684
SP - 315
EP - 322
BT - 2021 IEEE International Conference on Big Knowledge
A2 - Gong, Zhiguo
A2 - Li, Xue
A2 - Oguducu, Sule Gunduz
A2 - Chen, Lei
A2 - Manjon, Baltasar Fernandez
A2 - Wu, Xindong
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 12th IEEE International Conference on Big Knowledge, ICBK 2021
Y2 - 7 December 2021 through 8 December 2021
ER -