Aggregating Continuous Word Embeddings for Information Retrieval

DMCA

Aggregating Continuous Word Embeddings for Information Retrieval

Cached

Download Links

by Stéphane Clinchant , Florent Perronnin

Citations:

2 - 0 self

BibTeX

@MISC{Clinchant_aggregatingcontinuous,
    author = {Stéphane Clinchant and Florent Perronnin},
    title = {Aggregating Continuous Word Embeddings for Information Retrieval},
    year = {}
}

OpenURL

Abstract

While words in documents are generally treated as discrete entities, they can be embedded in a Euclidean space which reflects an a priori notion of similarity between them. In such a case, a text document can be viewed as a bag-ofembedded-words (BoEW): a set of realvalued vectors. We propose a novel document representation based on such continuous word embeddings. It consists in non-linearly mapping the wordembeddings in a higher-dimensional space and in aggregating them into a documentlevel representation. We report retrieval and clustering experiments in the case where the word-embeddings are computed from standard topic models showing significant improvements with respect to the original topic models. 1

Keyphrases

continuous word embeddings information retrieval significant improvement realvalued vector euclidean space discrete entity documentlevel representation text document standard topic model novel document representation priori notion higher-dimensional space original topic model

DMCA