What does this research mean for the field?

A convolutional neural network trained to predict hashtags from short textual posts learns semantic text representations that are highly effective for both hashtag prediction and downstream tasks like document recommendation. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

January 1, 2014

#TagSpace: Semantic Embeddings from Hashtags

Key Points

Key points are not available for this paper at this time.

Abstract

We describe a convolutional neural net-work that learns feature representations for short textual posts using hashtags as a su-pervised signal. The proposed approach is trained on up to 5.5 billion words predict-ing 100,000 possible hashtags. As well as strong performance on the hashtag predic-tion task itself, we show that its learned representation of text (ignoring the hash-tag labels) is useful for other tasks as well. To that end, we present results on a docu-ment recommendation task, where it also outperforms a number of baselines. 1

Mark Helpful

Bookmark

Relay