Recurrent Context Window Networks for Italian Named Entity Recognizer (original) (raw)

2016, Italian Journal of Computational Linguistics

Sign up for access to the world's latest research.

checkGet notified about relevant papers

checkSave papers to use in your research

checkJoin the discussion with peers

checkTrack your impact

Italian named entity recognizer participation in NER task@ Evalita 09

Proceedings of EVALITA, 2009

In this paper, we present our system for Named Entity Recognition (NER), as one of the significantly important preliminary steps prior to main Natural Language Processing tasks, based on Support Vector Machines and feature extraction and selection. The system performed the third best on the task of Italian NER at EVALITA 2009, with an overall F-measure of 81.09, which has less than one percent gap with the best result (82 %).

KIND: an Italian Multi-Domain Dataset for Named Entity Recognition

arXiv (Cornell University), 2021

In this paper we present KIND, an Italian dataset for Named-entity recognition. It contains more than one million tokens with annotation covering three classes: person, location, and organization. The dataset (around 600K tokens) mostly contains manual gold annotations in three different domains (news, literature, and political discourses) and a semi-automatically annotated part. The multi-domain feature is the main strength of the present work, offering a resource which covers different styles and language uses, as well as the largest Italian NER dataset with manual gold annotations. It represents an important resource for the training of NER systems in Italian. Texts and annotations are freely downloadable from the Github repository.

Named Entity Recognition with Stack Residual LSTM and Trainable Bias Decoding

2017

Recurrent Neural Network models are the state-of-the-art for Named Entity Recognition (NER). We present two innovations to improve the performance of these models. The first innovation is the introduction of residual connections between the Stacked Recurrent Neural Network model to address the degradation problem of deep neural networks. The second innovation is a bias decoding mechanism that allows the trained system to adapt to non-differentiable and externally computed objectives, such as the entity-based F-measure. Our work improves the state-of-the-art results for both Spanish and English languages on the standard train/development/test split of the CoNLL 2003 Shared Task NER dataset.

Loading...

Loading Preview

Sorry, preview is currently unavailable. You can download the paper by clicking the button above.