Breaking Through the 80\% Glass Ceiling: Raising the State of the Art in Word Sense Disambiguation by Incorporating Knowledge Graph Information

ACL 2020  ·  Michele Bevilacqua, Roberto Navigli ·

Neural architectures are the current state of the art in Word Sense Disambiguation (WSD). However, they make limited use of the vast amount of relational information encoded in Lexical Knowledge Bases (LKB). We present Enhanced WSD Integrating Synset Embeddings and Relations (EWISER), a neural supervised architecture that is able to tap into this wealth of knowledge by embedding information from the LKB graph within the neural architecture, and to exploit pretrained synset embeddings, enabling the network to predict synsets that are not in the training set. As a result, we set a new state of the art on almost all the evaluation settings considered, also breaking through, for the first time, the 80{\%} ceiling on the concatenation of all the standard all-words English WSD evaluation benchmarks. On multilingual all-words WSD, we report state-of-the-art results by training on nothing but English.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Word Sense Disambiguation Supervised: EWISER+WNGC Senseval 2 80.8 # 6
Senseval 3 79.0 # 5
SemEval 2007 75.2 # 6
SemEval 2013 80.7 # 6
SemEval 2015 81.8 # 8
Word Sense Disambiguation Supervised: EWISER Senseval 2 78.9 # 10
Senseval 3 78.4 # 6
SemEval 2007 71.0 # 11
SemEval 2013 78.9 # 9
SemEval 2015 79.3 # 12

Methods


No methods listed for this paper. Add relevant methods here