About

SyntagNet is a manually-curated large-scale lexical-semantic combination database which associates pairs of concepts with pairs of co-occurring words, hence capturing sense distinctions evoked by syntagmatic relations.

SyntagNet was created starting from lexical combinations extracted from the English Wikipedia and the British National Corpus, and manually disambiguated according to the WordNet 3.0 inventory.

SyntagNet covers 78,000 noun-verb and noun-noun lexical combinations, with 88,019 semantic combinations linking 20,626 WordNet 3.0 unique synsets with a relation edge.

This website provides:

• a web interface for looking up terms and their lexical-semantic combinations (with hyperlinks pointing to BabelNet);
• an integrated interface to query SyntagRank, a knowledge-based disambiguation system which exploits SyntagNet relations to perform state-of-the-art disambiguation in five languages (English, German, French, Spanish, and Italian);
• statistics, a bibliography and a download section.

PUBLICATIONS

Marco Maru, Federico Scozzafava, Federico Martelli and Roberto Navigli. SyntagNet: Challenging Supervised Word Sense Disambiguation with Lexical-Semantic Combinations. Proc. of the 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP 2019), Hong Kong, China, November 3-7, 2019.

Federico Scozzafava, Marco Maru, Fabrizio Brignone, Giovanni Torrisi and Roberto Navigli. Personalized PageRank with Syntagmatic Information for Multilingual Word Sense Disambiguation. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, Seattle, WA, USA, July 5-10, 2020.

The authors gratefully acknowledge the support of the ERC Consolidator Grant MOUSSE No. 726487 and the ELEXIS project No. 731015 under the European Union’s Horizon 2020 research and innovation programme.