Abstract
Topics generated by topic models are typically presented as a list of topic terms. Automatic topic labelling is the task of generating a succinct label that summarises the theme or subject of a topic, with the intention of reducing the cognitive load of end-users when interpreting these topics. Traditionally, topic label systems focus on a single label modality, e.g. textual labels. In this work we propose a multimodal approach to topic labelling using a simple feedforward neural network. Given a topic and a candidate image or textual label, our method automatically generates a rating for the label, relative to the topic. Experiments show that this multimodal approach outperforms single-modality topic labelling systems.- Anthology ID:
- E17-2111
- Volume:
- Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers
- Month:
- April
- Year:
- 2017
- Address:
- Valencia, Spain
- Editors:
- Mirella Lapata, Phil Blunsom, Alexander Koller
- Venue:
- EACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 701–706
- Language:
- URL:
- https://aclanthology.org/E17-2111
- DOI:
- Cite (ACL):
- Ionut Sorodoc, Jey Han Lau, Nikolaos Aletras, and Timothy Baldwin. 2017. Multimodal Topic Labelling. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, pages 701–706, Valencia, Spain. Association for Computational Linguistics.
- Cite (Informal):
- Multimodal Topic Labelling (Sorodoc et al., EACL 2017)
- PDF:
- https://preview.aclanthology.org/ml4al-ingestion/E17-2111.pdf