# Evaluating Neural Word Representations in Tensor-Based Compositional Settings

arXiv: https://arxiv.org/abs/1408.6179 · HTML: https://mlsanity.com/paper/1408.6179/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Aug 2014.

## Built on by (most cited first, 7 of 7)

- [Corpus-Based Paraphrase Detection Experiments and Review](https://mlsanity.com/paper/2106.00145/) (2021)
- [Linguistics and Human Brain: A Perspective of Computational Neuroscience](https://mlsanity.com/paper/2602.08275/) (2026)
- [Extending Multi-Sense Word Embedding to Phrases and Sentences for Unsupervised Semantic Applications](https://mlsanity.com/paper/2103.15330/) (2021)
- [Should Semantic Vector Composition be Explicit? Can it be Linear?](https://mlsanity.com/paper/2104.06555/) (2021)
- [Vector Space Semantics for Lambek Calculus with Soft Subexponentials](https://mlsanity.com/paper/2111.11331/) (2021)
- [Comparing in context: Improving cosine similarity measures with a metric tensor](https://mlsanity.com/paper/2203.14996/) (2022)
- [Pregroup Grammars, their Syntax and Semantics](https://mlsanity.com/paper/2109.11237/) (2021)

## Abstract (arXiv)

We provide a comparative study between neural word representations and traditional vector spaces based on co-occurrence counts, in a number of compositional tasks. We use three different semantic spaces and implement seven tensor-based compositional models, which we then test (together with simpler additive and multiplicative approaches) in tasks involving verb disambiguation and sentence similarity. To check their scalability, we additionally evaluate the spaces using simple compositional methods on larger-scale tasks with less constrained language: paraphrase detection and dialogue act tagging. In the more constrained tasks, co-occurrence vectors are competitive, although choice of compositional method is important; on the larger-scale tasks, they are outperformed by neural word embeddings, which show robust, stable performance across the tasks.