Details
| Original language | English |
|---|---|
| Title of host publication | Cross-lingual Event-centric Open Analytics |
| Subtitle of host publication | Proceedings of the 1st International Workshop on Cross-lingual Event-centric Open Analytics co-located with the 17th Extended Semantic Web Conference (ESWC 2020) |
| Pages | 43-56 |
| Number of pages | 14 |
| Publication status | Published - 2020 |
| Externally published | Yes |
| Event | 1st International Workshop on Cross-Lingual Event-Centric Open Analytics, CLEOPATRA 2020 - Heraklion, Crete, Greece Duration: 3 Jun 2020 → … |
Publication series
| Name | CEUR Workshop Proceedings |
|---|---|
| Publisher | CEUR WS |
| Volume | 2611 |
| ISSN (Print) | 1613-0073 |
Abstract
Content-based information retrieval is based on the information contained in documents rather than using metadata such as keywords. Most information retrieval methods are either based on text or image. In this paper, we investigate the usefulness of multimodal features for cross-lingual news search in various domains: politics, health, environment, sport, and finance. To this end, we consider five feature types for image and text and compare the performance of the retrieval system using different combinations. Experimental results show that retrieval results can be improved when considering both visual and textual information. In addition, it is observed that among textual features entity overlap outperforms word embeddings, while geolocation embeddings achieve better performance among visual features in the retrieval task.
Keywords
- Computer Vision, Multimodal Features, Multimodal News Retrieval, Natural Language Processing
ASJC Scopus subject areas
- Computer Science(all)
- General Computer Science
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
Cross-lingual Event-centric Open Analytics: Proceedings of the 1st International Workshop on Cross-lingual Event-centric Open Analytics co-located with the 17th Extended Semantic Web Conference (ESWC 2020). 2020. p. 43-56 (CEUR Workshop Proceedings; Vol. 2611).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - A feature analysis for multimodal news retrieval
AU - Tahmasebzadeh, Golsa
AU - Hakimov, Sherzod
AU - Müller-Budack, Eric
AU - Ewerth, Ralph
N1 - Funding information: This project has received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Sk lodowska-Curie grant agreement no 812997.
PY - 2020
Y1 - 2020
N2 - Content-based information retrieval is based on the information contained in documents rather than using metadata such as keywords. Most information retrieval methods are either based on text or image. In this paper, we investigate the usefulness of multimodal features for cross-lingual news search in various domains: politics, health, environment, sport, and finance. To this end, we consider five feature types for image and text and compare the performance of the retrieval system using different combinations. Experimental results show that retrieval results can be improved when considering both visual and textual information. In addition, it is observed that among textual features entity overlap outperforms word embeddings, while geolocation embeddings achieve better performance among visual features in the retrieval task.
AB - Content-based information retrieval is based on the information contained in documents rather than using metadata such as keywords. Most information retrieval methods are either based on text or image. In this paper, we investigate the usefulness of multimodal features for cross-lingual news search in various domains: politics, health, environment, sport, and finance. To this end, we consider five feature types for image and text and compare the performance of the retrieval system using different combinations. Experimental results show that retrieval results can be improved when considering both visual and textual information. In addition, it is observed that among textual features entity overlap outperforms word embeddings, while geolocation embeddings achieve better performance among visual features in the retrieval task.
KW - Computer Vision
KW - Multimodal Features
KW - Multimodal News Retrieval
KW - Natural Language Processing
UR - http://www.scopus.com/inward/record.url?scp=85091095061&partnerID=8YFLogxK
U2 - 10.48550/arXiv.2007.06390
DO - 10.48550/arXiv.2007.06390
M3 - Conference contribution
AN - SCOPUS:85091095061
T3 - CEUR Workshop Proceedings
SP - 43
EP - 56
BT - Cross-lingual Event-centric Open Analytics
T2 - 1st International Workshop on Cross-Lingual Event-Centric Open Analytics, CLEOPATRA 2020
Y2 - 3 June 2020
ER -