# Intrinsic analysis for dual word embedding space models

arXiv: https://arxiv.org/abs/2012.00728 · HTML: https://mlsanity.com/paper/2012.00728/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Dec 2020.

## Built on by (most cited first, 2 of 2)

- [DEAP-FAKED: Knowledge Graph based Approach for Fake News Detection](https://mlsanity.com/paper/2107.10648/) (2021)
- [PESTS: Persian_English Cross Lingual Corpus for Semantic Textual Similarity](https://mlsanity.com/paper/2305.07893/) (2023)

## Abstract (arXiv)

Recent word embeddings techniques represent words in a continuous vector space, moving away from the atomic and sparse representations of the past. Each such technique can further create multiple varieties of embeddings based on different settings of hyper-parameters like embedding dimension size, context window size and training method. One additional variety appears when we especially consider the Dual embedding space techniques which generate not one but two-word embeddings as output. This gives rise to an interesting question - "is there one or a combination of the two word embeddings variety, which works better for a specific task?". This paper tries to answer this question by considering all of these variations. Herein, we compare two classical embedding methods belonging to two different methodologies - Word2Vec from window-based and Glove from count-based. For an extensive evaluation after considering all variations, a total of 84 different models were compared against semantic, association and analogy evaluations tasks which are made up of 9 open-source linguistics datasets. The final Word2vec reports showcase the preference of non-default model for 2 out of 3 tasks. In case of Glove, non-default models outperform in all 3 evaluation tasks.