Exportar Publicação

Coelho, J., Neto, A., Tavares, M., Coutinho, C., Oliveira, J., Ribeiro, R....Batista, F. (2021). Transformer-based language models for semantic search and mobile applications retrieval. In Cucchiara, R., Fred, A., & Filipe, J. (Ed.), Proceedings of the 13th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management. (pp. 225-232).: SCITEPRESS – Science and Technology Publications, Lda.

J. Coelho et al.,  "Transformer-based language models for semantic search and mobile applications retrieval", in Proc. of the 13th Int. Joint Conf. on Knowledge Discovery, Knowledge Engineering and Knowledge Management, Cucchiara, R., Fred, A., & Filipe, J., Ed., SCITEPRESS – Science and Technology Publications, Lda, 2021, vol. 1, pp. 225-232

@inproceedings{coelho2021_1735272772383,
	author = "Coelho, J. and Neto, A. and Tavares, M. and Coutinho, C. and Oliveira, J. and Ribeiro, R. and Batista, F.",
	title = "Transformer-based language models for semantic search and mobile applications retrieval",
	booktitle = "Proceedings of the 13th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management",
	year = "2021",
	editor = "Cucchiara, R., Fred, A., & Filipe, J.",
	volume = "1",
	number = "",
	series = "",
	doi = "10.5220/0010657300003064",
	pages = "225-232",
	publisher = "SCITEPRESS – Science and Technology Publications, Lda",
	address = "",
	organization = "INSTICC - Institute for Systems and Technologies of Information, Control and Communication",
	url = "https://www.scitepress.org/ProceedingsDetails.aspx?ID=cBXMJ72+CEw=&t=1"
}

TY  - CPAPER
TI  - Transformer-based language models for semantic search and mobile applications retrieval
T2  - Proceedings of the 13th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management
VL  - 1
AU  - Coelho, J.
AU  - Neto, A.
AU  - Tavares, M.
AU  - Coutinho, C.
AU  - Oliveira, J.
AU  - Ribeiro, R.
AU  - Batista, F.
PY  - 2021
SP  - 225-232
SN  - 2184-3228
DO  - 10.5220/0010657300003064
UR  - https://www.scitepress.org/ProceedingsDetails.aspx?ID=cBXMJ72+CEw=&t=1
AB  - Search engines are being extensively used by Mobile App Stores, where millions of users world-wide use them every day. However, some stores still resort to simple lexical-based search engines, despite the recent advances in Machine Learning, Information Retrieval, and Natural Language Processing, which allow for richer semantic strategies. This work proposes an approach for semantic search of mobile applications that relies on transformer-based language models, fine-tuned with the existing textual information about known mobile applications. Our approach relies solely on the application name and on the unstructured textual information contained in its description. A dataset of about 500 thousand mobile apps was extended in the scope of this work with a test set, and all the available textual data was used to fine-tune our neural language models. We have evaluated our models using a public dataset that includes information about 43 thousand applications, and 56 manually annotated non- exact queries. The results show that our model surpasses the performance of all the other retrieval strategies reported in the literature. Tests with users have confirmed the performance of our semantic search approach, when compared with an existing deployed solution.
ER  -