Semantic search of mobile applications using word embeddings
| Autor: | Coelho, João, Neto, António, Tavares, Miguel, Coutinho, Carlos, Ribeiro, Ricardo, Batista, Fernando |
|---|---|
| Přispěvatelé: | Queirós. R., Pinto, M., Simões, A., Portela, F., & Pereira, M. J. |
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Ciências Sociais::Geografia Económica e Social [Domínio/Área Científica]
Information systems → Retrieval models and ranking Information systems → Search engine indexing Word Embeddings Mobile Applications Information systems → Language models Information systems → Similarity measures Mobile applications Elasticsearch Ciências Naturais::Matemáticas [Domínio/Área Científica] Computing methodologies → Machine learning Word embeddings Semantic search Information systems → Document representation Semantic Search |
| Popis: | This paper proposes a set of approaches for the semantic search of mobile applications, based on their name and on the unstructured textual information contained in their description. The proposed approaches make use of word-level, character-level, and contextual word-embeddings that have been trained or fine-tuned using a dataset of about 500 thousand mobile apps, collected in the scope of this work. The proposed approaches have been evaluated using a public dataset that includes information about 43 thousand applications, and 56 manually annotated non-exact queries. Our results show that both character-level embeddings trained on our data, and fine-tuned RoBERTa models surpass the performance of the other existing retrieval strategies reported in the literature. OASIcs, Vol. 94, 10th Symposium on Languages, Applications and Technologies (SLATE 2021), pages 12:1-12:12 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|