Paper: #TagSpace: Semantic Embeddings from Hashtags

ACL ID D14-1194
Title #TagSpace: Semantic Embeddings from Hashtags
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2014
Authors

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.