Representation learning for very short texts using weighted word embedding aggregation

TL;DR

This paper introduces a weighted word embedding aggregation method for very short texts, improving semantic representation and outperforming baselines on Wikipedia and Twitter data.

Contribution

The paper proposes a novel weighted embedding aggregation model with a median-based loss function for better short text semantics.

Findings

Outperforms baseline methods in experiments

Generalizes well across different embeddings

Retains most semantic information in short texts

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.