Transfer Learning for Domain-Specific Named Entity Recognition in German
Research output: Contribution to book/Conference proceedings/Anthology/Report › Conference contribution › Contributed › peer-review
Contributors
Abstract
Automated text analysis as named entity recognition (NER) heavily relies on large amounts of high-quality training data. Transfer learning approaches aim to overcome the problem of lacking domain-specific training data. In this paper, we investigate different transfer learning approaches to recognize unknown domain-specific entities, including the influence on varying training data size. The experiments are based on the revised German SmartData Corpus, and a baseline model, trained on this corpus.
Details
| Original language | English |
|---|---|
| Title of host publication | 6th International IEEE Congress on Information Science and Technology, CiSt 2020 - Proceeding |
| Editors | Mohammed El Mohajir, Mohammed Al Achhab, Badr Eddine El Mohajir, Bernadetta Kwintiana Ane, Ismail Jellouli |
| Publisher | Wiley-IEEE Press |
| Pages | 321-327 |
| Number of pages | 7 |
| ISBN (electronic) | 9781728166469 |
| ISBN (print) | 978-1-7281-6647-6 |
| Publication status | Published - 12 Jun 2021 |
| Peer-reviewed | Yes |
Conference
| Title | 2020 6th IEEE Congress on Information Science and Technology (CiSt) |
|---|---|
| Duration | 5 - 12 June 2021 |
| Location | Agadir - Essaouira, Morocco |
External IDs
| Scopus | 85103860847 |
|---|---|
| Ieee | 10.1109/CiSt49399.2021.9357262 |
| ORCID | /0000-0001-9756-6390/work/154741803 |
Keywords
ASJC Scopus subject areas
Keywords
- Annotations, Data models, Text recognition, Training, Training data, Transfer learning, Vocabulary, NER, Named Entity Recognition System, transfer learning, Named Entity Recognition, Transfer Learning, Domain-specific, BiLSTM-CRF, German