Entity Projection via Machine Translation for Cross-Lingual NER

Jain, Alankar; Paranjape, Bhargavi

doi:10.48550/arxiv.1909.05356

Cited by 5 publications

(8 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The quality of the annotation will be evaluated through crowdsourcing tasks and, lastly, we will propagate the corrected annotations from the English corpus to those in other languages. This final process will be done by employing existing label propagation algorithms and models, such as graph propagation methods [22] and machine-translation models [10].…”

Section: Application Methodologymentioning

confidence: 99%

UNER: Universal Named-Entity RecognitionFramework

Alves,

Kuculo,

Amaral

et al. 2020

Preprint

View full text Add to dashboard Cite

We introduce the Universal Named-Entity Recognition (UNER) framework, a 4-level classification hierarchy, and the methodology that is being adopted to create the first multilingual UNER corpus: the SETimes parallel corpus annotated for named-entities. First, the English SETimes corpus will be annotated using existing tools and knowledge bases. After evaluating the resulting annotations through crowdsourcing campaigns, they will be propagated automatically to other languages within the SE-Times corpora. Finally, as an extrinsic evaluation, the UNER multilingual dataset will be used to train and test available NER tools. As part of future research directions, we aim to increase the number of languages in the UNER corpus and to investigate possible ways of integrating UNER with available knowledge graphs to improve named-entity recognition.

show abstract

Section: Application Methodologymentioning

confidence: 99%

UNER: Universal Named-Entity RecognitionFramework

Alves,

Kuculo,

Amaral

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Developments in semantics and Named Entity Recognition (NER) for Armenian have been noteworthy, as exhibited by the research conducted by Mkhitaryan and Madatyan (2022); Podolak and Zeinert (2020); Jain et al (2019); Tambuscio and Andrews (2021); Vachagan and Tigran (2015); Ghukasyan et al (2018).…”

Section: Advancements In Semantics and Namedmentioning

confidence: 99%

“…Cross-Lingual NER: Multilingual transformer models were investigated by Podolak and Zeinert (2020) to understand the influence of languagespecific features on performance. Meanwhile, Jain et al (2019) leveraged machine translation to enhance NER in languages with sparsely annotated corpora, exhibiting superior performance for Armenian NER compared to a monolingual model.…”

Section: Advancements In Semantics and Namedmentioning

confidence: 99%

Large Language Models and Low-Resource Languages: An Examination of Armenian NLP

Avetisyan,

Broneske

2023

Findings of the Association for Computational Linguistics: IJCNLP-AACL 2023 (Findings)

View full text Add to dashboard Cite

This paper presents a comprehensive review of Natural Language Processing (NLP) research on Armenian, a language that, despite its rich history and unique linguistic characteristics, is currently low-resource in the field of NLP. We critically synthesize and evaluate various studies in Armenian NLP, highlighting key advancements, challenges, and areas for improvement. A notable aspect of our work is the underlined lack of application of Large Language Models (LLMs) in Armenian NLP, signifying an area of potential exploration and development. Identifying and discussing these challenges and opportunities lays the groundwork for future research directions in Armenian NLP. The emphasis on Armenian also advocates for increased attention to low-resource languages in NLP research, stressing the importance of linguistic diversity and equity. To the best of our knowledge, this is the first paper providing such an extensive review of Armenian NLP, marking a significant contribution to the field.

show abstract

“…Named Entity Recognition (NER) is the task of identifying and classifying named entities in unstructured text into predefined categories such as people, organizations, locations, disease names, drug mentions, among others (li et al, 2020). NER is widely used in various applications such as information extraction and retrieval (Jiang et al, 2016), question answering (Liu et al, 2020), word sense disambiguation (Jarrar et al, 2023a;Al-Hajj and Jarrar, 2021), machine translation (Jain et al, 2019;Khurana et al, 2022), automatic summarization (Summerscales et al, 2011;Khurana et al, 2022), interoperability and cybersecurity (Tikhomirov et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

Arabic Fine-Grained Entity Recognition

Liqreina,

Jarrar,

Khalilia

et al. 2023

Proceedings of ArabicNLP 2023

View full text Add to dashboard Cite

Traditional NER systems are typically trained to recognize coarse-grained entities, and less attention is given to classifying entities into a hierarchy of fine-grained lower-level subtypes. This article aims to advance Arabic NER with finegrained entities. We chose to extend Wojood (an open-source Nested Arabic Named Entity Corpus) with subtypes. In particular, four main entity types in Wojood, geopolitical entity (GPE), location (LOC), organization (ORG), and facility (FAC), are extended with 31 subtypes. To do this, we first revised Wojood's annotations of GPE, LOC, ORG, and FAC to be compatible with the LDC's ACE guidelines, which yielded 5, 614 changes. Second, all mentions of GPE, LOC, ORG, and FAC (∼ 44K) in Wojood are manually annotated with the LDC's ACE subtypes. We refer to this extended version of Wojood as WojoodF ine. To evaluate our annotations, we measured the inter-annotator agreement (IAA) using both Cohen's Kappa and F1 score, resulting in 0.9861 and 0.9889, respectively. To compute the baselines of WojoodF ine, we finetune three pre-trained Arabic BERT encoders in three settings: flat NER, nested NER and nested NER with subtypes and achieved F1 score of 0.920, 0.866, and 0.885, respectively. Our corpus and models are open-source and available at https://sina.birzeit.edu/wojood/.

show abstract

Entity Projection via Machine Translation for Cross-Lingual NER

Cited by 5 publications

References 0 publications

UNER: Universal Named-Entity RecognitionFramework

UNER: Universal Named-Entity RecognitionFramework

Large Language Models and Low-Resource Languages: An Examination of Armenian NLP

Arabic Fine-Grained Entity Recognition

Contact Info

Product

Resources

About