maindoc.bib

@inproceedings{wikiann,
  title     = {Cross-lingual Name Tagging and Linking for 282 Languages},
  author    = {Pan, Xiaoman  and
               Zhang, Boliang  and
               May, Jonathan  and
               Nothman, Joel  and
               Knight, Kevin  and
               Ji, Heng},
  booktitle = {Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  month     = jul,
  year      = {2017},
  address   = {Vancouver, Canada},
  publisher = {Association for Computational Linguistics},
  url       = {https://aclanthology.org/P17-1178},
  doi       = {10.18653/v1/P17-1178},
  pages     = {1946--1958},
  abstract  = {The ambitious goal of this work is to develop a cross-lingual name tagging and linking framework for 282 languages that exist in Wikipedia. Given a document in any of these languages, our framework is able to identify name mentions, assign a coarse-grained or fine-grained type to each mention, and link it to an English Knowledge Base (KB) if it is linkable. We achieve this goal by performing a series of new KB mining methods: generating {``}silver-standard{''} annotations by transferring annotations from English to other languages through cross-lingual links and KB properties, refining annotations through self-training and topic selection, deriving language-specific morphology features from anchor links, and mining word translation pairs from cross-lingual links. Both name tagging and linking results for 282 languages are promising on Wikipedia data and on-Wikipedia data.}
}


@article{nner-survey,
  author     = {Wang, Yu and Tong, Hanghang and Zhu, Ziye and Li, Yun},
  title      = {Nested Named Entity Recognition: A Survey},
  year       = {2022},
  issue_date = {December 2022},
  publisher  = {Association for Computing Machinery},
  address    = {New York, NY, USA},
  volume     = {16},
  number     = {6},
  issn       = {1556-4681},
  url        = {https://doi.org/10.1145/3522593},
  doi        = {10.1145/3522593},
  abstract   = {With the rapid development of text mining, many studies observe that text generally contains a variety of implicit information, and it is important to develop techniques for extracting such information. Named Entity Recognition (NER), the first step of information extraction, mainly identifies names of persons, locations, and organizations in text. Although existing neural-based NER approaches achieve great success in many language domains, most of them normally ignore the nested nature of named entities. Recently, diverse studies focus on the nested NER problem and yield state-of-the-art performance. This survey attempts to provide a comprehensive review on existing approaches for nested NER from the perspectives of the model architecture and the model property, which may help readers have a better understanding of the current research status and ideas. In this survey, we first introduce the background of nested NER, especially the differences between nested NER and traditional (i.e., flat) NER. We then review the existing nested NER approaches from 2002 to 2020 and mainly classify them into five categories according to the model architecture, including early rule-based, layered-based, region-based, hypergraph-based, and transition-based approaches. We also explore in greater depth the impact of key properties unique to nested NER approaches from the model property perspective, namely entity dependency, stage framework, error propagation, and tag scheme. Finally, we summarize the open challenges and point out a few possible future directions in this area. This survey would be useful for three kinds of readers: (i) Newcomers in the field who want to learn about NER, especially for nested NER. (ii) Researchers who want to clarify the relationship and advantages between flat NER and nested NER. (iii) Practitioners who just need to determine which NER technique (i.e., nested or not) works best in their applications.},
  journal    = {ACM Trans. Knowl. Discov. Data},
  month      = jul,
  articleno  = {108},
  numpages   = {29},
  keywords   = {Nested named entity recognition, named entity recognition, information extraction, natural language processing, text mining}
}
@article{li2019unified,
  title   = {A Unified MRC Framework for Named Entity Recognition},
  author  = {Li, Xiaoya and Feng, Jingrong and Meng, Yuxian and Han, Qinghong and Wu, Fei and Li, Jiwei},
  journal = {arXiv preprint arXiv:1910.11476},
  year    = {2019}
}
@misc{devlin2019bert,
  title         = {BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding},
  author        = {Jacob Devlin and Ming-Wei Chang and Kenton Lee and Kristina Toutanova},
  year          = {2019},
  eprint        = {1810.04805},
  archiveprefix = {arXiv},
  primaryclass  = {cs.CL}
}
@inproceedings{germeval2014,
  title     = {NoSta-D Named Entity Annotation for German: Guidelines and Dataset},
  author    = {Benikova, Darina  and
               Biemann, Chris  and
               Reznicek, Marc},
  booktitle = {Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)},
  month     = may,
  year      = {2014},
  address   = {Reykjavik, Iceland},
  publisher = {European Language Resources Association (ELRA)},
  url       = {http://www.lrec-conf.org/proceedings/lrec2014/pdf/276_Paper.pdf},
  pages     = {2524--2531}
}
@inproceedings{gbert,
  title     = {{G}erman{'}s Next Language Model},
  author    = {Chan, Branden  and
               Schweter, Stefan  and
               M{\"o}ller, Timo},
  booktitle = {Proceedings of the 28th International Conference on Computational Linguistics},
  month     = dec,
  year      = {2020},
  address   = {Barcelona, Spain (Online)},
  publisher = {International Committee on Computational Linguistics},
  url       = {https://aclanthology.org/2020.coling-main.598},
  doi       = {10.18653/v1/2020.coling-main.598},
  pages     = {6788--6796},
  abstract  = {In this work we present the experiments which lead to the creation of our BERT and ELECTRA based German language models, GBERT and GELECTRA. By varying the input training data, model size, and the presence of Whole Word Masking (WWM) we were able to attain SoTA performance across a set of document classification and named entity recognition (NER) tasks for both models of base and large size. We adopt an evaluation driven approach in training these models and our results indicate that both adding more data and utilizing WWM improve model performance. By benchmarking against existing German models, we show that these models are the best German models to date. All trained models will be made publicly available to the research community.}
}
@inproceedings{multinerd,
  title     = {{M}ulti{NERD}: A Multilingual, Multi-Genre and Fine-Grained Dataset for Named Entity Recognition (and Disambiguation)},
  author    = {Tedeschi, Simone  and
               Navigli, Roberto},
  booktitle = {Findings of the Association for Computational Linguistics: NAACL 2022},
  month     = jul,
  year      = {2022},
  address   = {Seattle, United States},
  publisher = {Association for Computational Linguistics},
  url       = {https://aclanthology.org/2022.findings-naacl.60},
  doi       = {10.18653/v1/2022.findings-naacl.60},
  pages     = {801--812},
  abstract  = {Named Entity Recognition (NER) is the task of identifying named entities in texts and classifying them through specific semantic categories, a process which is crucial for a wide range of NLP applications. Current datasets for NER focus mainly on coarse-grained entity types, tend to consider a single textual genre and to cover a narrow set of languages, thus limiting the general applicability of NER systems.In this work, we design a new methodology for automatically producing NER annotations, and address the aforementioned limitations by introducing a novel dataset that covers 10 languages, 15 NER categories and 2 textual genres.We also introduce a manually-annotated test set, and extensively evaluate the quality of our novel dataset on both this new test set and standard benchmarks for NER.In addition, in our dataset, we include: i) disambiguation information to enable the development of multilingual entity linking systems, and ii) image URLs to encourage the creation of multimodal systems.We release our dataset at https://github.com/Babelscape/multinerd.}
}
@inproceedings{europeana,
  title     = {An Open Corpus for Named Entity Recognition in Historic Newspapers},
  author    = {Neudecker, Clemens},
  booktitle = {Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)},
  month     = may,
  year      = {2016},
  address   = {Portoro{\v{z}}, Slovenia},
  publisher = {European Language Resources Association (ELRA)},
  url       = {https://aclanthology.org/L16-1689},
  pages     = {4348--4352},
  abstract  = {The availability of openly available textual datasets ({``}corpora{''}) with highly accurate manual annotations ({``}gold standard{''}) of named entities (e.g. persons, locations, organizations, etc.) is crucial in the training and evaluation of named entity recognition systems. Currently there are only few such datasets available on the web, and even less for texts containing historical spelling variation. The production and subsequent release into the public domain of four such datasets with 100 pages each for the languages Dutch, French, German (including Austrian) as part of the Europeana Newspapers project is expected to contribute to the further development and improvement of named entity recognition systems with a focus on historical content. This paper describes how these datasets were produced, what challenges were encountered in their creation and informs about their final quality and availability.}
}

@misc{bert-base-german-cased,
  title  = {bert-base-german-cased · Hugging Face},
  author = {Branden Chan and
            Malte Pietsch and
            Timo Möller and
            Tanay Soni},
  year   = {2019},
  month  = {06},
  day    = {14},
  url    = {https://huggingface.co/bert-base-german-cased}
}

@misc{Schiesser_2023,
  title  = {mschiesser/ner-bert-german · hugging face},
  url    = {https://huggingface.co/mschiesser/ner-bert-german},
  author = {Schiesser, Marcus},
  year   = {2023},
  month  = {03},
  day    = {23}
} 
@inproceedings{riedl-pado-shootout,
  title     = {A Named Entity Recognition Shootout for {G}erman},
  author    = {Riedl, Martin  and
               Pad{\'o}, Sebastian},
  booktitle = {Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)},
  month     = jul,
  year      = {2018},
  address   = {Melbourne, Australia},
  publisher = {Association for Computational Linguistics},
  url       = {https://aclanthology.org/P18-2020},
  doi       = {10.18653/v1/P18-2020},
  pages     = {120--125},
  abstract  = {We ask how to practically build a model for German named entity recognition (NER) that performs at the state of the art for both contemporary and historical texts, i.e., a big-data and a small-data scenario. The two best-performing model families are pitted against each other (linear-chain CRFs and BiLSTM) to observe the trade-off between expressiveness and data requirements. BiLSTM outperforms the CRF when large datasets are available and performs inferior for the smallest dataset. BiLSTMs profit substantially from transfer learning, which enables them to be trained on multiple corpora, resulting in a new state-of-the-art model for German NER on two contemporary German corpora (CoNLL 2003 and GermEval 2014) and two historic corpora.}
}