#TagSpace: Semantic Embeddings from Hashtags
EMNLP, pp. 1822-1827, 2014.
We argue that hashtag prediction provides a more direct form of supervision: the tags are a labeling by the author of the salient aspects of the text
We describe a convolutional neural network that learns feature representations for short textual posts using hashtags as a supervised signal. The proposed approach is trained on up to 5.5 billion words predicting 100,000 possible hashtags. As well as strong performance on the hashtag prediction task itself, we show that its learned repres...More
PPT (Upload PPT)