ConceptNet at SemEval-2017 Task 2: Extending Word Embeddings with Multilingual Relational Knowledge
This work addresses the challenge of improving semantic similarity tasks for NLP researchers and practitioners, but it is incremental as it updates previous methods.
The paper tackled the problem of multilingual and cross-lingual semantic word similarity by extending word embeddings with ConceptNet, a multilingual knowledge graph, achieving first place in both subtasks of SemEval 2017 Task 2, including ranking first in 4 out of 5 languages and all 10 cross-lingual pairs.
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.