Sanaphor++: Combining Deep Neural Networks with Semantics for Coreference Resolution
Sanaphor++: Combining Deep Neural Networks with Semantics for Coreference Resolution
复制标题
DOI：
--
复制
发表时间：
2018-05
期刊：
影响因子：
--
通讯作者：
J. Plu;Roman Prokofyev;Alberto Tonon;P. Cudré-Mauroux;D. Difallah;Raphael Troncy;Giuseppe Rizzo
中科院分区：
文献类型：
--
作者：
J. Plu;Roman Prokofyev;Alberto Tonon;P. Cudré-Mauroux;D. Difallah;Raphael Troncy;Giuseppe Rizzo
指代消解一直是自然语言处理中的一项具有挑战性的任务。随着时间的推移，机器学习和语义技术改善了技术水平，尽管几年来，最大的进步是使用深度神经网络。在本文中，我们描述了Sanphor++，它是对顶级深度神经网络系统Stanford Deep-coref的改进，它通过添加语义特征来实现指代消解。SANNAFOR++的目标是改进共指解析的聚类部分，以便知道一旦已经识别了提及对，是否必须合并两个聚类。fi我们在CoNLL 2012共享任务数据集上对我们的模型进行了评估，并将其与最先进的系统(Stanford Deep-coref)进行了比较，在该系统中，我们展示了F1平均得分的1.13%的平均收益。
Coreference resolution has always been a challenging task in Natural Language Processing. Machine learning and semantic techniques have improved the state of the art over the time, though since a few years, the biggest step forward has been made using deep neural networks. In this paper, we describe Sanaphor++, which is an improvement of a top-level deep neural network system for coreference resolution—namely Stanford deep-coref—through the addition of semantic features. The goal of Sanaphor++ is to improve the clustering part of the coreference resolution in order to know if two clusters have to be merged or not once the pairs of mentions have been identified. We evaluate our model over the CoNLL 2012 Shared Task dataset and compare it with the state-of-the-art system (Stanford deep-coref) where we demonstrated an average gain of 1.13% of the average F1 score.