Neural Architectures for Nested NER through Linearization

Straková, Jana; Straka, Milan; Hajič, Jan

doi:10.18653/v1/p19-1527

Cited by 205 publications

(141 citation statements)

References 21 publications

Supporting

Mentioning

131

Contrasting

Order By: Relevance

“…Lin et al [34] proposed a sequence-to-nugget architecture that uses a head-driven phrase structure for nested NE recognition. In Table 7, the BERT is used in Xia et al [55], Fisher et al [56], Shibuya et al [57], StrakovÂt'a et al [59] and Jue et al [84]. Compared with them, our model achieves state-of-theart performance in the task of nested NE recognition.…”

Section: Comparing With Other Methodsmentioning

confidence: 99%

See 1 more Smart Citation

A Boundary Assembling Method for Nested Biomedical Named Entity Recognition

Chen

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Biomedical named entity recognition (BNER) is an important task in biomedical natural language processing, in which neologisms (new terms, words) are coined constantly. Most of the existing work can only identify biomedical named entities with flattened structures and ignore nested biomedical named entities and discontinuous biomedical named entities. Because biomedical domains often use nested structures to represent semantic information of named entities, existing methods fail to utilize abundant information when processing biomedical texts. This paper focuses on identifying nested biomedical named entities using a boundary assembly (BA) model, which is a cascading framework consisting of three steps. First, start and end named entity boundaries are identified and then assembled into named entity candidates. Finally, a classifier is implemented for filtering false named entities. Our approach is effective in handling nesting and discontinuous problems in biomedical named entity recognition tasks. It improves the performance considerably, achieving an F1-score of 81.34% on the GENIA dataset.

show abstract

Section: Comparing With Other Methodsmentioning

confidence: 99%

“…Lin et al [34] proposed a sequence-to-nugget architecture that uses a headdriven phrase structure for nested NE recognition. Recently, pretrained language models have shown valuable potential to improve performance [55]- [59], [84].…”

Section: Related Workmentioning

confidence: 99%

A Boundary Assembling Method for Nested Biomedical Named Entity Recognition

Chen

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Their method developed the multitask mechanism to improve the recall of the clinical named-entity recognition. Straková [ 24 ] proposed two neural network architectures for nested NER, and the ELMo contextual embeddings were used to enrich their architectures. Dogan et al [ 25 ] proposed a framework that incorporated deep learning models of ELMo with Wikidata to address the issue of the lack of datasets for the task of fine-grained NER.…”

Section: Related Workmentioning

confidence: 99%

Semi-Supervised Bidirectional Long Short-Term Memory and Conditional Random Fields Model for Named-Entity Recognition Using Embeddings from Language Models Representations

Zhang

Geng

Chen

2020

Entropy

View full text Add to dashboard Cite

Increasingly, popular online museums have significantly changed the way people acquire cultural knowledge. These online museums have been generating abundant amounts of cultural relics data. In recent years, researchers have used deep learning models that can automatically extract complex features and have rich representation capabilities to implement named-entity recognition (NER). However, the lack of labeled data in the field of cultural relics makes it difficult for deep learning models that rely on labeled data to achieve excellent performance. To address this problem, this paper proposes a semi-supervised deep learning model named SCRNER (Semi-supervised model for Cultural Relics’ Named Entity Recognition) that utilizes the bidirectional long short-term memory (BiLSTM) and conditional random fields (CRF) model trained by seldom labeled data and abundant unlabeled data to attain an effective performance. To satisfy the semi-supervised sample selection, we propose a repeat-labeled (relabeled) strategy to select samples of high confidence to enlarge the training set iteratively. In addition, we use embeddings from language model (ELMo) representations to dynamically acquire word representations as the input of the model to solve the problem of the blurred boundaries of cultural objects and Chinese characteristics of texts in the field of cultural relics. Experimental results demonstrate that our proposed model, trained on limited labeled data, achieves an effective performance in the task of named entity recognition of cultural relics.

show abstract

“…We use a novel approach [37] for nested named entity recognition (NER) to capture the nested entities in the Czech Named Entity Corpus. The nested entities are encoded in a sequence and the problem of nested NER is then viewed as a sequence-to-sequence (seq2seq) problem, in which the input sequence consists of the input tokens (forms) and the output sequence of the linearized entity labels.…”

Section: Named Entity Recognitionmentioning

confidence: 99%

Czech Text Processing with Contextual Embeddings: POS Tagging, Lemmatization, Parsing and NER

Straka

Straková

Hajič

2019

Text, Speech, and Dialogue

Self Cite

View full text Add to dashboard Cite

Contextualized embeddings, which capture appropriate word meaning depending on context, have recently been proposed. We evaluate two methods for precomputing such embeddings, BERT and Flair, on four Czech text processing tasks: part-of-speech (POS) tagging, lemmatization, dependency parsing and named entity recognition (NER). The first three tasks, POS tagging, lemmatization and dependency parsing, are evaluated on two corpora: the Prague Dependency Treebank 3.5 and the Universal Dependencies 2.3. The named entity recognition (NER) is evaluated on the Czech Named Entity Corpus 1.1 and 2.0. We report state-of-the-art results for the above mentioned tasks and corpora.

show abstract

Neural Architectures for Nested NER through Linearization

Cited by 205 publications

References 21 publications

A Boundary Assembling Method for Nested Biomedical Named Entity Recognition

A Boundary Assembling Method for Nested Biomedical Named Entity Recognition

Semi-Supervised Bidirectional Long Short-Term Memory and Conditional Random Fields Model for Named-Entity Recognition Using Embeddings from Language Models Representations

Czech Text Processing with Contextual Embeddings: POS Tagging, Lemmatization, Parsing and NER

Contact Info

Product

Resources

About