# ConceptNet at SemEval-2017 Task 2: Extending Word Embeddings with Multilingual Relational Knowledge

## TL;DR

This paper presents a system that enhances multilingual word embeddings with ConceptNet's relational knowledge, achieving top performance in SemEval-2017 Task 2 for semantic word similarity across multiple languages.

## Contribution

It introduces an improved method for integrating ConceptNet with distributional semantics to produce high-quality multilingual embeddings, outperforming previous approaches.

## Key findings

- Ranked first in 4 out of 5 languages
- Achieved top scores in all cross-lingual pairs
- Demonstrated effectiveness of ConceptNet integration

## Abstract

This paper describes Luminoso's participation in SemEval 2017 Task 2, "Multilingual and Cross-lingual Semantic Word Similarity", with a system based on ConceptNet. ConceptNet is an open, multilingual knowledge graph that focuses on general knowledge that relates the meanings of words and phrases. Our submission to SemEval was an update of previous work that builds high-quality, multilingual word embeddings from a combination of ConceptNet and distributional semantics. Our system took first place in both subtasks. It ranked first in 4 out of 5 of the separate languages, and also ranked first in all 10 of the cross-lingual language pairs.