Neural Architectures for Named Entity Recognition
Guillaume Lample, Miguel Ballesteros, Sandeep Subramanian, Kazuya Kawakami, Chris Dyer
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/clab/stack-lstm-nerOfficialIn papernone★ 0
- github.com/glample/taggerOfficialIn papernone★ 0
- github.com/flairNLP/flairpytorch★ 14,353
- github.com/samueljamesbell/sequence-labelertf★ 11
- github.com/maviccprp/ger_ner_evalsnone★ 0
- github.com/UcasLzz/ChineseWordSeg-POSnone★ 0
- github.com/PKU-TANGENT/nlp-tutorialpytorch★ 0
- github.com/IBM/MAX-Named-Entity-Taggertf★ 0
- github.com/Hironsan/anagonone★ 0
- github.com/IsabelMeraner/BotanicalNERnone★ 0
Abstract
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.
Tasks
Benchmark Results
| Dataset | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| CoNLL++ | LSTM-CRF | F1 | 91.47 | — | Unverified |
| CoNLL 2003 (English) | LSTM-CRF | F1 | 90.94 | — | Unverified |