Representation learning for very short texts using weighted word embedding aggregation

July 02, 2016 Β· Declared Dead Β· πŸ› Pattern Recognition Letters

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Cedric De Boom, Steven Van Canneyt, Thomas Demeester, Bart Dhoedt arXiv ID 1607.00570 Category cs.IR: Information Retrieval Cross-listed cs.CL Citations 197 Venue Pattern Recognition Letters Last Checked 4 months ago
Abstract
Short text messages such as tweets are very noisy and sparse in their use of vocabulary. Traditional textual representations, such as tf-idf, have difficulty grasping the semantic meaning of such texts, which is important in applications such as event detection, opinion mining, news recommendation, etc. We constructed a method based on semantic word embeddings and frequency information to arrive at low-dimensional representations for short texts designed to capture semantic similarity. For this purpose we designed a weight-based model and a learning procedure based on a novel median-based loss function. This paper discusses the details of our model and the optimization methods, together with the experimental results on both Wikipedia and Twitter data. We find that our method outperforms the baseline approaches in the experiments, and that it generalizes well on different word embeddings without retraining. Our method is therefore capable of retaining most of the semantic information in the text, and is applicable out-of-the-box.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Information Retrieval

Died the same way β€” πŸ‘» Ghosted