Corpus specificity in LSA and Word2vec: the role of out-of-domain documents

TL;DR

This paper compares how corpus size and domain specificity affect the performance of LSA and Word2vec in capturing semantic relations, revealing that Word2vec benefits from larger corpora while LSA improves with domain-specific, reduced datasets.

Contribution

It demonstrates that corpus domain specificity enhances LSA performance and that Word2vec benefits from larger, comprehensive corpora, providing insights into their different mechanisms.

Findings

Word2vec performs best with the entire corpus.

LSA improves with domain-specific, reduced datasets.

Specialization can reduce LSA performance if dimensionality isn't decreased.

Abstract

Latent Semantic Analysis (LSA) and Word2vec are some of the most widely used word embeddings. Despite the popularity of these techniques, the precise mechanisms by which they acquire new semantic relations between words remain unclear. In the present article we investigate whether LSA and Word2vec capacity to identify relevant semantic dimensions increases with size of corpus. One intuitive hypothesis is that the capacity to identify relevant dimensions should increase as the amount of data increases. However, if corpus size grow in topics which are not specific to the domain of interest, signal to noise ratio may weaken. Here we set to examine and distinguish these alternative hypothesis. To investigate the effect of corpus specificity and size in word-embeddings we study two ways for progressive elimination of documents: the elimination of random documents vs. the elimination of documents unrelated to a specific task. We show that Word2vec can take advantage of all the documents, obtaining its best performance when it is trained with the whole corpus. On the contrary, the specialization (removal of out-of-domain documents) of the training corpus, accompanied by a decrease of dimensionality, can increase LSA word-representation quality while speeding up the processing time. Furthermore, we show that the specialization without the decrease in LSA dimensionality can produce a strong performance reduction in specific tasks. From a cognitive-modeling point of view, we point out that LSA's word-knowledge acquisitions may not be efficiently exploiting higher-order co-occurrences and global relations, whereas Word2vec does.