A Morpho-Syntactically Informed LSTM-CRF Model for Named Entity Recognition

Abstract

We propose a morphologically informed model for named entity recognition, which is based on LSTM-CRF architecture and combines word embeddings, Bi-LSTM character embeddings, part-of-speech (POS) tags, and morphological information. While previous work has focused on learning from raw word input, using word and character embeddings only, we show that for morphologically rich languages, such as Bulgarian, access to POS information contributes more to the performance gains than the detailed morphological information. Thus, we show that named entity recognition needs only coarse-grained POS tags, but at the same time it can benefit from simultaneously using some POS information of different granularity. Our evaluation results over a standard dataset show sizable improvements over the state-of-the-art for Bulgarian NER.

arXiv commentnamed entity recognition; Bulgarian NER; morphology; morpho-syntax

References in corpus (8)

• Efficient Estimation of Word Representations in Vector Space
• Improving neural networks by preventing co-adaptation of feature detectors
• XLNet: Generalized Autoregressive Pretraining for Language Understanding
• Long Short-Term Memory Based Recurrent Neural Network Architectures for Large Vocabulary Speech Recognition
• Multi-Task Deep Neural Networks for Natural Language Understanding
• Improving Multi-Task Deep Neural Networks via Knowledge Distillation for Natural Language Understanding
• Feature-Rich Named Entity Recognition for Bulgarian Using Conditional Random Fields
• Application of a Hybrid Bi-LSTM-CRF model to the task of Russian Named Entity Recognition