We study the open-domain named entity recognition (NER) problem under distant
supervision. The distant supervision, though does not require large amounts of manual …

The ambitious goal of this work is to develop a cross-lingual name tagging and linking
framework for 282 languages that exist in Wikipedia. Given a document in any of these …

Traditional approaches to the task of ACE event extraction usually rely on sequential
pipelines with multiple stages, which suffer from error propagation since event triggers and …

We propose a new neural transfer method termed Dual Adversarial Transfer Network
(DATNet) for addressing low-resource Named Entity Recognition (NER). Specifically, two …

摘要传统的机器学习假设测试样本和训练样本来自同一概率分布. 但当前很多学习场景下训练
样本和测试样本可能来自不同的概率分布. 域自适应学习能够有效地解决训练样本和测试样本 …

Distant supervised relation extraction (RE) has been an effective way of finding novel
relational facts from text without labeled training data. Typically it can be formalized as a …

Weak supervision has shown promising results in many natural language processing tasks,
such as Named Entity Recognition (NER). Existing work mainly focuses on learning deep …

In this paper we give an overview of the Entity Discovery and Linking tasks at the Knowledge
Base Population track at TAC 2014. In this year we introduced a new end-to-end English …

Neural networks have been widely used for high resource language (eg English) named
entity recognition (NER) and have shown state-of-the-art results. However, for low resource …

Different languages contain complementary cues about entities, which can be used to
improve Named Entity Recognition (NER) systems. We propose a method that formulates …