A Morpho-Syntactically Informed LSTM-CRF Model for Named Entity Recognition
This work addresses named entity recognition for morphologically rich languages like Bulgarian, offering incremental improvements by optimizing feature usage.
The paper tackled named entity recognition for morphologically rich languages by proposing an LSTM-CRF model that incorporates word embeddings, character embeddings, and part-of-speech tags, showing that POS tags contribute more than detailed morphological information. Evaluation on a standard Bulgarian dataset demonstrated sizable improvements over the state-of-the-art.
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.