# Learning Meta-Embeddings by Using Ensembles of Embedding Sets

arXiv: https://arxiv.org/abs/1508.04257 · HTML: https://mlsanity.com/paper/1508.04257/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Aug 2015.

## Built on by (most cited first, 3 of 3)

- [FacTeR-Check: Semi-automated fact-checking through Semantic Similarity and Natural Language Inference](https://mlsanity.com/paper/2110.14532/) (2021)
- [Gender Bias in Meta-Embeddings](https://mlsanity.com/paper/2205.09867/) (2022)
- [Learning Meta Word Embeddings by Unsupervised Weighted Concatenation of Source Embeddings](https://mlsanity.com/paper/2204.12386/) (2022)

## Abstract (arXiv)

Word embeddings -- distributed representations of words -- in deep learning are beneficial for many tasks in natural language processing (NLP). However, different embedding sets vary greatly in quality and characteristics of the captured semantics. Instead of relying on a more advanced algorithm for embedding learning, this paper proposes an ensemble approach of combining different public embedding sets with the aim of learning meta-embeddings. Experiments on word similarity and analogy tasks and on part-of-speech tagging show better performance of meta-embeddings compared to individual embedding sets. One advantage of meta-embeddings is the increased vocabulary coverage. We will release our meta-embeddings publicly.