no code implementations • International Conference on Data Mining Workshops (ICDMW) 2022 • Stavroula Skylaki, Ali Oskooei, Omar Bari, Nadja Herger, Zac Kriegman
To overcome the challenges of our noisy training data, e. g., text extraction errors and/or typos and unknown label indices, we frame the NER task as a sequence generation task (seq2seq) and train a pointer generator network to generate the entities in the document rather than label them.
no code implementations • 17 Dec 2020 • Stavroula Skylaki, Ali Oskooei, Omar Bari, Nadja Herger, Zac Kriegman
Named Entity Recognition (NER) is the task of identifying and classifying named entities in unstructured text.