Neural Architectures for Named Entity Recognition
Objekt
Titel
Neural Architectures for Named Entity Recognition
arXiv:1603.01360 [cs]
Urheber
Guillaume Lample
Miguel Ballesteros
Sandeep Subramanian
Kazuya Kawakami
Chris Dyer
Thema
Computer Science - Computation and Language
Zusammenfassung
State-of-the-art named entity recognition systems rely heavily on hand-crafted features and domain-specific knowledge in order to learn effectively from the small, supervised training corpora that are available. In this paper, we introduce two new neural architectures---one based on bidirectional LSTMs and conditional random fields, and the other that constructs and labels segments using a transition-based approach inspired by shift-reduce parsers. Our models rely on two sources of information about words: character-based word representations learned from the supervised corpus and unsupervised word representations learned from unannotated corpora. Our models obtain state-of-the-art performance in NER in four languages without resorting to any language-specific knowledge or resources such as gazetteers.
Datum
2016-03-04
