Year: 2020
Type: conference-paper
Abstract: booktitle= {Proceedings of The 12th Language Resources and Evaluation Conference}, month = {May}, year = {2020}, address = {Marseille, France}, publisher = {European Language Resources Association}, pages = {1--10}, abstract = {Mention detection is an important preprocessing step for annotation and interpretation in applications such as NER and coreference resolution, but few stand-alone neural models have been proposed able to handle the full range of mentions.In this work, we propose and compare three neural network-based approaches to mention detection.The first approach is based on the mention detection part of a state of the art coreference resolution system; the second uses ELMO embeddings together with a bidirectional LSTM and a biaffine classifier; the third approach uses the recently introduced BERT model.Our best model (using a biaffine classifier) achieves gains of up to 1.8 percentage points on mention recall when compared with a strong baseline in a HIGH RECALL coreference annotation setting.The same model achieves improvements of up to 5.3 and 6.2 p.p. when compared with the best-reported mention detection F1 on the CONLL and CRAC coreference data sets respectively in a HIGH F1 annotation setting.We then evaluate our models for coreference resolution by using mentions predicted by our best model in start-of-the-art coreference systems.The enhanced model achieved absolute improvements of up to 1.7 and 0.7 p.p. when compared with our strong baseline systems (pipeline system and end-to-end system) respectively.For nested NER, the evaluation of our model on the GENIA corpora shows that our model matches or outperforms state-ofthe-art models despite not being specifically designed for this task.},url = {https://www.aclweb.
Source: HAL
Institutions: Institute for Computational Linguistics “A. Zampolli”, Aix-Marseille Université, Laboratoire d’Informatique et Systèmes, Centre National de la Recherche Scientifique, Laboratoire Parole et Langage, Evaluations and Language resources Distribution Agency, German Research Centre for Artificial Intelligence, National Institute of Information and Communications Technology, University of Copenhagen, Common Language Resources and Technology Infrastructure, Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur, Universitat de Barcelona, Utrecht University, Institute for Language and Speech Processing
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4391418904