Nested Named Entity Recognition

44 papers with code • 6 benchmarks • 11 datasets

Nested named entity recognition is a subtask of information extraction that seeks to locate and classify nested named entities (i.e., hierarchically structured entities) mentioned in unstructured text (Source: Adapted from Wikipedia).

Most implemented papers

Locate and Label: A Two-stage Identifier for Nested Named Entity Recognition

tricktreat/locate-and-label ACL 2021

Although these methods have the innate ability to handle nested NER, they suffer from high computational cost, ignorance of boundary information, under-utilization of the spans that partially match with entities, and difficulties in long entity recognition.

A Sequence-to-Set Network for Nested Named Entity Recognition

zqtan1024/sequence-to-set 19 May 2021

We utilize a non-autoregressive decoder to predict the final set of entities in one pass, in which we are able to capture dependencies between entities.

A Unified Generative Framework for Various NER Subtasks

yhcc/BARTNER ACL 2021

To that end, we propose to formulate the NER subtasks as an entity span sequence generation task, which can be solved by a unified sequence-to-sequence (Seq2Seq) framework.

Bottom-Up Constituency Parsing and Nested Named Entity Recognition with Pointer Networks

sustcsonglin/pointer-net-for-nested ACL 2022

Constituency parsing and nested named entity recognition (NER) are similar tasks since they both aim to predict a collection of nested and non-crossing spans.

Fusing Heterogeneous Factors with Triaffine Mechanism for Nested Named Entity Recognition

GanjinZero/Triaffine-nested-ner Findings (ACL) 2022

To fuse these heterogeneous factors, we propose a novel triaffine mechanism including triaffine attention and scoring.

Unified Named Entity Recognition as Word-Word Relation Classification

ljynlp/w2ner 19 Dec 2021

So far, named entity recognition (NER) has been involved with three major types, including flat, overlapped (aka.

Nested Named Entity Recognition as Latent Lexicalized Constituency Parsing

louchao98/nner_as_parsing ACL 2022

They treat nested entities as partially-observed constituency trees and propose the masked inside algorithm for partial marginalization.

Parallel Instance Query Network for Named Entity Recognition

tricktreat/piqn ACL 2022

Each instance query predicts one entity, and by feeding all instance queries simultaneously, we can query all entities in parallel.

Automatic Extraction of Nested Entities in Clinical Referrals in Spanish

plncmm/acm_health_msen ACM Transactions on Computing for Healthcare 2022

The annotated corpus, clinical word embeddings, annotation guidelines, and neural models are freely released to the community.