Distributed Representations of Sentences and Documents
This addresses the need for better text representations in machine learning, offering a novel unsupervised method that improves performance over existing techniques.
The paper tackles the problem of representing variable-length texts as fixed-length vectors, proposing Paragraph Vector to overcome bag-of-words weaknesses like loss of word order and semantics, achieving new state-of-the-art results on text classification and sentiment analysis tasks.
Many machine learning algorithms require the input to be represented as a fixed-length feature vector. When it comes to texts, one of the most common fixed-length features is bag-of-words. Despite their popularity, bag-of-words features have two major weaknesses: they lose the ordering of the words and they also ignore semantics of the words. For example, "powerful," "strong" and "Paris" are equally distant. In this paper, we propose Paragraph Vector, an unsupervised algorithm that learns fixed-length feature representations from variable-length pieces of texts, such as sentences, paragraphs, and documents. Our algorithm represents each document by a dense vector which is trained to predict words in the document. Its construction gives our algorithm the potential to overcome the weaknesses of bag-of-words models. Empirical results show that Paragraph Vectors outperform bag-of-words models as well as other techniques for text representations. Finally, we achieve new state-of-the-art results on several text classification and sentiment analysis tasks.