SapienzaNLP @ ACL2020
4 Papers at ACL!
Breaking Through the 80% Glass Ceiling: Raising the State of the Art in Word Sense Disambiguation by Incorporating Knowledge Graph Information
Michele Bevilacqua and Roberto Navigli
EWISER is a state-of-the-art Word Sense Disambiguation architecture that incorporates both synset embeddings and WordNet relations, seamlessly integrating diverse knowledge. Website: github.com/SapienzaNLP/ewiser
CluBERT: A Cluster-Based Approach for Learning Sense Distributions in Multiple Languages
Tommaso Pasini, Federico Scozzafava and Bianca Scarlini
CluBERT is an automatic and multilingual approach to infer the distribution of word meanings from a corpus or raw sentences, aiding domain adaptation in different languages.
Fatality Killed the Cat or: BabelPic, a Multimodal Dataset for Non-Concrete Concepts
Agostina Calabrese, Michele Bevilacqua and Roberto Navigli
BabelPic is the first multimodal dataset with a focus on non-concrete concepts which is also linked to WordNet and BabelNet. Plus: it can be automatically extended to any BabelNet synset.
Personalized PageRank with Syntagmatic Information for Multilingual Word Sense Disambiguation
Federico Scozzafava, Marco Maru, Fabrizio Brignone, Giovanni Torrisi and Roberto Navigli
SyntagRank is a state-of-the-art knowledge-based system for multilingual Word Sense Disambiguation using syntagmatic information, freely available via Web interface and APIs! Joint work between SapienzaNLP and babelscape.