Luminoso

A Luminoso is a Multilingual and Cross-lingual Semantic Word Similarity System that is based on ConceptNet.

• AKA: Luminoso Semantic Word Similarity System.
• Context:
  • It was the best overall performing semantic word similarity system in the SemEval-2017 Task 2.
• Example(s):
  • …
• Counter-Example(s):
  • HCCL,
  • SEW-Embed,
  • Mahtab,
  • QLUT,
  • Citius,
  • jmp8,
  • l2f,
  • RUFINO,
  • MERALI,
  • hhu,
  • Wild Devs,
  • OoO,
  • NASARI.
• See: SemEval, SemEval-2017 Task, Semantic Word Similarity Benchmark Task, Semantic Textual Similarity Benchmark Task, Semantic Similarity Modelling System, Semantic Similarity Measure, Semantic Relatedness Measure.

---

---

References

2017a

• (Camacho-Collados et al., 2017) ⇒ Jose Camacho-Collados, Mohammad Taher Pilehvar, Nigel Collier, and Roberto Navigli. (2017). “SemEval-2017 Task 2: Multilingual and Cross-lingual Semantic Word Similarity.” In: Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval ACL 2017).
  • QUOTE: Luminoso achieved the best results in all languages except Farsi. Luminoso couples word embeddings with knowledge from ConceptNet (Speer et al., 2017) using an extension of Retrofitting (Faruqui et al., 2015), which proved highly effective. This system additionally proposed two fallback strategies to handle out-of-vocabulary (OOV) instances based on loan-words and cognates. These two fallback strategies proved essential given the amount of rare words or domain-specific words which were present in the datasets. In fact, most systems fail to provide scores for all pairs in the datasets, with OOV rates close to 10% in some cases.

2017b

• (Speer & Lowry-Duda, 2017) ⇒ Robyn Speer, and Joanna Lowry-Duda. (2017). “ConceptNet at SemEval-2017 Task 2: Extending Word Embeddings with Multilingual Relational Knowledge.” In: Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval@ACL 2017).
  • QUOTE: The system we submitted to SemEval-2017 Task 2, “Multilingual and Cross-lingual Semantic Word Similarity”, is an update of that system, coinciding with the release of version 5.5.3 of ConceptNet. We added multiple fallback methods for assigning vectors to out-of-vocabulary words. We also experimented with, but did not submit, systems that used additional sources of word embeddings in the five languages of this SemEval task

2015

• (Faruqui et al., 2015) ⇒ Manaal Faruqui, Jesse Dodge, Sujay Kumar Jauhar, Chris Dyer, Eduard H. Hovy, and Noah A. Smith. (2015). “Retrofitting Word Vectors to Semantic Lexicons.” In: Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT 2015).

---