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

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, usi...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2019-08
Main Authors: Simeonova, Lilia, Simov, Kiril, Osenova, Petya, Nakov, Preslav
Format: Article
Language:English
Subjects:
Morphology
Recognition
Tags
Words (language)
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2331-8422