Learning bag-of-embedded-words representations for textual information retrieval
作者：
Highlights：
• A novel BoF-based model is proposed for efficiently representing text documents.
• A weighting mask (similar to the traditional BoW weighting schemes) is learned.
• The BoEW is optimized end-to-end (from the word embeddings to the weighting mask).
• The learned representation can be efficiently finetuned using relevance feedback.
• The proposed method is evaluated using three text collections from different domains.
摘要
•A novel BoF-based model is proposed for efficiently representing text documents.•A weighting mask (similar to the traditional BoW weighting schemes) is learned.•The BoEW is optimized end-to-end (from the word embeddings to the weighting mask).•The learned representation can be efficiently finetuned using relevance feedback.•The proposed method is evaluated using three text collections from different domains.
论文关键词：Word embeddings,Bag-of-words,Bag-of-features,Dictionary learning,Relevance feedback,Information retrieval
论文评审过程：Received 23 October 2017, Revised 9 February 2018, Accepted 8 April 2018, Available online 10 April 2018, Version of Record 18 April 2018.
论文官网地址：https://doi.org/10.1016/j.patcog.2018.04.008
