Spherical Paragraph Model

TL;DR

The paper introduces the Spherical Paragraph Model, a probabilistic approach leveraging word embeddings to generate semantically rich text representations, achieving state-of-the-art results in classification tasks.

Contribution

It presents a novel probabilistic generative model based on word embeddings that better captures semantic relatedness for text representation.

Findings

Achieves state-of-the-art performance on benchmark datasets

Effectively leverages word co-occurrence and corpus-wide information

Provides a probabilistic framework with interpretability

Abstract

Representing texts as fixed-length vectors is central to many language processing tasks. Most traditional methods build text representations based on the simple Bag-of-Words (BoW) representation, which loses the rich semantic relations between words. Recent advances in natural language processing have shown that semantically meaningful representations of words can be efficiently acquired by distributed models, making it possible to build text representations based on a better foundation called the Bag-of-Word-Embedding (BoWE) representation. However, existing text representation methods using BoWE often lack sound probabilistic foundations or cannot well capture the semantic relatedness encoded in word vectors. To address these problems, we introduce the Spherical Paragraph Model (SPM), a probabilistic generative model based on BoWE, for text representation. SPM has good probabilistic interpretability and can fully leverage the rich semantics of words, the word co-occurrence information as well as the corpus-wide information to help the representation learning of texts. Experimental results on topical classification and sentiment analysis demonstrate that SPM can achieve new state-of-the-art performances on several benchmark datasets.