Handling negative samples problems in span-based nested named entity recognition

Liu, Chenxu; Fan, Hongjie; Liu, Junfei

doi:10.1016/j.neucom.2022.07.012

Cited by 14 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We note that the best obtained results of nested NER for NEREL-BIO are lower than for general NEREL dataset, on which the MRC model achieved more than 80% micro-F-measure. This is in line with existing published NER results that also show similar decreased results on biomedical texts ( Shibuya and Hovy 2020 ; Liu et al 2022 ). The results for second-best sequence model are closest to the MRC model in micro measures but significantly worse in macro measures.…”

Section: Experiments and Evaluationsupporting

confidence: 92%

NEREL-BIO: a dataset of biomedical abstracts annotated with nested named entities

et al. 2023

View full text Add to dashboard Cite

Motivation This paper describes NEREL-BIO – an annotation scheme and corpus of PubMed abstracts in Russian and smaller number of abstracts in English. NEREL-BIO extends the general domain dataset NEREL (Loukachevitch et al., 2021) by introducing domain-specific entity types. NEREL-BIO annotation scheme covers both general and biomedical domains making it suitable for domain transfer experiments. NEREL-BIO provides annotation for nested named entities as an extension of the scheme employed for NEREL. Nested named entities may cross entity boundaries to connect to shorter entities nested within longer entities, making them harder to detect. Results NEREL-BIO contains annotations for 700+ Russian and 100+ English abstracts. All English PubMed annotations have corresponding Russian counterparts. Thus, NEREL-BIO comprises the following specific features: annotation of nested named entities, it can be used as a benchmark for cross-domain (NEREL → NEREL-BIO) and cross-language (English → Russian) transfer. We experiment with both transformer-based sequence models and machine reading comprehension (MRC) models and report their results. Availability The dataset and annotation guidelines are freely available at https://github.com/nerel-ds/NEREL-BIO.

show abstract

Section: Experiments and Evaluationsupporting

confidence: 92%

NEREL-BIO: a dataset of biomedical abstracts annotated with nested named entities

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Conversely, 7 harnessed a bi-affine attention mechanism to classify boundary span representations. In contrast, 20 proposes the strategy of dividing the NER task into two subtasks (specifically entity recognition and entity classification) to mitigate the challenges associated with negative samples in span-based approaches.In order to address the problem of ignoring semantic relationships between spans in span-based approaches, 8 introduced a planarized sentence representation that enables semantic interactions between spans by merging the head and tail entity representations into a 3D feature matrix and employing a convolutional neural network.…”

Section: Related Workmentioning

confidence: 99%

Bi-Directional Context-Aware Networks for the Nested Named Entity Recognition

Li,

Liao,

Yan

et al. 2024

Preprint

View full text Add to dashboard Cite

A prevalent method for nested named entity recognition involves enumerating all potential entity spans within a given sentence, considering these spans as potential entity types, and subsequently subjecting them to classification. Nevertheless, this span-centric approach traditionally undertakes the decoding of each entity span independently, neglecting the underlying semantic connections that exist between these spans, as well as the valuable information pertaining to the specific locations of the head and tail tokens within each span. Therefore, we introduced a bidirectional context-aware network specifically engineered to model and elucidate the semantic relationships that underpin these spans. Additionally, we improve the bi-affine mechanism by introducing rotational position coding to capture the relative position information between the head and tail markers. We carried out experiments on three nested datasets, producing convincing outcomes that firmly demonstrate the superior performance of our model compared to existing models, particularly in terms of F1 scores.

show abstract