An evaluation of recent neural sequence tagging models in Turkish named entity recognition

•Performances of LSTM and transformer-based networks are studied for Turkish NER.•A new transformer-based network with a CRF layer on top is introduced.•The state-of-the-art Turkish NER results are obtained with the proposed network Named entity recognition (NER) is an extensively studied task that...

Full description

Saved in:
Bibliographic Details
Published in:Expert systems with applications 2021-11, Vol.182, p.115049, Article 115049
Main Authors: Aras, Gizem, Makaroğlu, Didem, Demir, Seniz, Cakir, Altan
Format: Article
Language:English
Subjects:
Conditional random fields
CRF
Digital media industry
Marking
Named entity recognition
Natural language processing
Networks
Real time operation
Recognition
Transfer learning
Transformers
Turkish
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•Performances of LSTM and transformer-based networks are studied for Turkish NER.•A new transformer-based network with a CRF layer on top is introduced.•The state-of-the-art Turkish NER results are obtained with the proposed network Named entity recognition (NER) is an extensively studied task that extracts and classifies named entities in a text. NER is crucial not only in downstream language processing applications such as relation extraction and question answering but also in large scale big data operations such as real-time analysis of online digital media content. Recent research efforts on Turkish, a less studied language with morphologically rich nature, have demonstrated the effectiveness of neural architectures on well-formed texts and yielded state-of-the art results by formulating the task as a sequence tagging problem. In this work, we empirically investigate the use of recent neural architectures (Bidirectional long short-term memory (BiLSTM) and Transformer-based networks) proposed for Turkish NER tagging in the same setting. Our results demonstrate that transformer-based networks which can model long-range context overcome the limitations of BiLSTM networks where different input features at the character, subword, and word levels are utilized. We also propose a transformer-based network with a conditional random field (CRF) layer that leads to the state-of-the-art result (95.95% f-measure) on a common dataset. Our study contributes to the literature that quantifies the impact of transfer learning on processing morphologically rich languages.
ISSN:0957-4174
1873-6793
DOI:10.1016/j.eswa.2021.115049