Injecting real-world information (typically contained in Knowledge Graphs) and human expertise into an end-to-end training pipeline for Natural Language Processing models is an open challenge. In this preliminary work, we propose to approach the task of Named Entity Recognition, which is traditionally viewed as a Sequence Tagging problem, as a Graph Classification problem, where every word is represented as a node in a graph. This allows to embed contextual information as well as other external knowledge relevant to each token, such as gazetteer mentions, morphological form, and linguistic tags. We experiment with a variety of graph modeling techniques to represent words, their contexts, and external knowledge, and we evaluate our approach on the standard CoNLL-2003 dataset. We obtained promising results when integrating external knowledge through the use of graph representation in comparison to the dominant end-to-end training paradigm.
Named entity recognition as graph classification
ESWC 2021, 18th Extended Semantic Web Conference, 6-10 June 2021, Hersonissos, Greece (Virtual Conference) / Also in LNCS, Vol.12739/2021
Poster / Demo
© Springer. Personal use of this material is permitted. The definitive version of this paper was published in ESWC 2021, 18th Extended Semantic Web Conference, 6-10 June 2021, Hersonissos, Greece (Virtual Conference) / Also in LNCS, Vol.12739/2021 and is available at : https://doi.org/10.1007/978-3-030-80418-3_19
PERMALINK : https://www.eurecom.fr/publication/6509