SU-NLP at SemEval-2022 Task 11: Complex Named Entity Recognition with Entity Linking
This work addresses the problem of recognizing complex named entities in low-context scenarios for natural language processing applications, representing an incremental advancement.
The paper tackled complex named entity recognition by developing an unsupervised entity linking pipeline using Wikipedia for mention detection and context, resulting in significant performance improvements, especially for complex entities in low-context settings.
This paper describes the system proposed by Sabancı University Natural Language Processing Group in the SemEval-2022 MultiCoNER task. We developed an unsupervised entity linking pipeline that detects potential entity mentions with the help of Wikipedia and also uses the corresponding Wikipedia context to help the classifier in finding the named entity type of that mention. Our results showed that our pipeline improved performance significantly, especially for complex entities in low-context settings.