DAMO-NLP at SemEval-2022 Task 11: A Knowledge-based System for Multilingual Named Entity Recognition

Wang, Xinyu; Shen, Yongliang; Cai, Jiong; Wang, Tao; Wang, Xiaobin; Xie, Pengjun; Huang, Fei; Lü, Weiming; Zhuang, Yueting; Tu, Kewei; Lü, Wei; Jiang, Yong

doi:10.48550/arxiv.2203.00545

Cited by 4 publications

(4 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the future, we would like to experiment with other model architectures for more complex NER tasks such as those presented at SemEval-2022 (Malmasi et al, 2022), of particular interest is the work from Wang et al (2022). We would like to include more native Quechua speaking annotators in order to improve the data set even more.…”

Section: Discussionmentioning

confidence: 99%

Proceedings of the Third Workshop on Deep Learning for Low-Resource Natural Language Processing

2022

View full text Add to dashboard Cite

The lack of resources for languages in the Americas has proven to be a problem for the creation of digital systems such as machine translation, search engines, chat bots, and more. The scarceness of digital resources for a language causes a higher impact on populations where the language is spoken by millions of people. We introduce the first official large combined corpus for deep learning of an indigenous South American low-resource language spoken by millions called Quechua. Specifically, our curated corpus is created from text gathered from the southern region of Peru where a dialect of Quechua is spoken that has not traditionally been used for digital systems as a target dialect in the past. In order to make our work repeatable by others, we also offer a public, pre-trained, BERT model called Qu-BERT which is the largest linguistic model ever trained for any Quechua type, not just the southern region dialect. We furthermore test our corpus and its corresponding BERT model on two major tasks: (1) named-entity recognition (NER) and (2) part-of-speech (POS) tagging by using state-of-the-art techniques where we achieve results comparable to other work on higher-resource languages. In this article, we describe the methodology, challenges, and results from the creation of QuBERT which is on on par with other state-of-the-art multilingual models for natural language processing achieving between 71 and 74% F1 score on NER and 84-87% on POS tasks. ReferencesWillem FH Adelaar. 2004. The languages of the Andes.

show abstract

Section: Discussionmentioning

confidence: 99%

Proceedings of the Third Workshop on Deep Learning for Low-Resource Natural Language Processing

2022

View full text Add to dashboard Cite

show abstract

“…In last year's MultiCoNER shared task, the two winning systems employed different strategies. [17] used a large-scale retrieval approach to gather relevant paragraphs related to the target sentence, which were concatenated and used as input to a transformer-CRF system. The aim was to build a multilingual knowledge base relying on Wikipedia.…”

Section: Related Workmentioning

confidence: 99%

Multilingual Fine-Grained Named Entity Recognition

Lupancu,

Iftene

2023

CSJM

View full text Add to dashboard Cite

The “MultiCoNER II Multilingual Complex Named Entity Recognition” task1 within SemEval 2023 competition focuses on identifying complex named entities (NEs), such as the titles of creative works (e.g., songs, books, movies), people with different titles (e.g., politicians, scientists, artists, athletes), different categories of products (e.g., food, drinks, clothing), and so on, in several languages. In the context of SemEval, our team, FII_Better, presented an exploration of a base transformer model’s capabilities regarding the task, focused more specifically on five languages (English, Spanish, Swedish, German, and Italian). We took DistilBERT (a distilled version of BERT) and BERT (Bidirectional Encoder Representations from Transformers) as two examples of basic transformer models, using DistilBERT as a baseline and BERT as the platform to create an improved model. In this process, we managed to get fair results in the chosen languages. We have managed to get moderate results in the English track (we ranked 17th out of 34), while our results in the other tracks could be further improved in the future (overall third to last).

show abstract

“…Wang et al [22] proposed a knowledge-based system for multilingual NER using a multi-stage fine-tuning approach for the MultiCoNER SemEval 2022 task 11 . Inspired by their multi-stage fine-tuning, we also adapt their approach for our final system.…”

Section: Multi-stage Fine-tuningmentioning

confidence: 99%

“…We also experimented with the knowledge-based system for multilingual NER that was proposed by Wang et al [22]. We used their implementation to enrich the original AjMC datasets with a knowledge base and implemented their context approach in the Flair library.…”

Section: Challengesmentioning

confidence: 99%

hmBERT: Historical Multilingual Language Models for Named Entity Recognition

Schweter¹,

März²,

Schmid³

et al. 2022

Preprint

View full text Add to dashboard Cite

Compared to standard Named Entity Recognition (NER), identifying persons, locations, and organizations in historical texts forms a big challenge. To obtain machine-readable corpora, the historical text is usually scanned and optical character recognition (OCR) needs to be performed. As a result, the historical corpora contain errors. Also, entities like location or organization can change over time, which poses another challenge. Overall historical texts come with several peculiarities that differ greatly from modern texts and large labeled corpora for training a neural tagger are hardly available for this domain. In this work, we tackle NER for historical German, English, French, Swedish, and Finnish by training large historical language models. We circumvent the need for labeled data by using unlabeled data for pretraining a language model. hmBert, a historical multilingual BERT-based language model is proposed, with different sizes of it being publicly released. Furthermore, we evaluate the capability of hmBert by solving downstream NER as part of this year's HIPE-2022 shared task and provide detailed analysis and insights. For the Multilingual Classical Commentary coarse-grained NER challenge, our tagger HISTeria outperforms the other teams' models for two out of three languages.

show abstract

DAMO-NLP at SemEval-2022 Task 11: A Knowledge-based System for Multilingual Named Entity Recognition

Cited by 4 publications

References 17 publications

Proceedings of the Third Workshop on Deep Learning for Low-Resource Natural Language Processing

Proceedings of the Third Workshop on Deep Learning for Low-Resource Natural Language Processing

Multilingual Fine-Grained Named Entity Recognition

hmBERT: Historical Multilingual Language Models for Named Entity Recognition

Contact Info

Product

Resources

About