Vector of Locally-Aggregated Word Embeddings (VLAWE): A Novel Document-level Representation

NAACL 2019 Radu Tudor IonescuAndrei M. Butnaru

In this paper, we propose a novel representation for text documents based on aggregating word embedding vectors into document embeddings. Our approach is inspired by the Vector of Locally-Aggregated Descriptors used for image representation, and it works as follows... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Document Classification Reuters-21578 VLAWE F1 89.3 # 1
Text Classification TREC-6 VLAWE Error 5.8 # 8