Towards Robust Word Embeddings for Noisy Texts
Use este enlace para citar
http://hdl.handle.net/2183/26682Coleccións
- GI-LYS - Artigos [43]
- OpenAIRE [264]
Metadatos
Mostrar o rexistro completo do ítemTítulo
Towards Robust Word Embeddings for Noisy TextsData
2020Cita bibliográfica
Doval Y, Vilares J, Gómez-Rodríguez C. Towards Robust Word Embeddings for Noisy Texts. Applied Sciences. 2020; 10(19):6893.
Resumo
[Abstract] Research on word embeddings has mainly focused on improving their performance on standard corpora, disregarding the difficulties posed by noisy texts in the form of tweets and other types of non-standard writing from social media. In this work, we propose a simple extension to the skipgram model in which we introduce the concept of bridge-words, which are artificial words added to the model to strengthen the similarity between standard words and their noisy variants. Our new embeddings outperform baseline models on noisy texts on a wide range of evaluation tasks,
both intrinsic and extrinsic, while retaining a good performance on standard texts. To the best of our knowledge, this is the first explicit approach at dealing with these types of noisy texts at the word embedding level that goes beyond the support for out-of-vocabulary words.
Palabras chave
Semantics
Word embeddings
Noisy texts
Social media
Natural language processing
Word embeddings
Noisy texts
Social media
Natural language processing
Versión do editor
Dereitos
Atribución 4.0
ISSN
2076-3417