A dynamic programming algorithm for span-based nested named-entity recognition in O(n^2)
Not on the map. Why?
Abstract (arXiv)
Span-based nested named-entity recognition (NER) has a cubic-time complexity using a variant of the CYK algorithm. We show that by adding a supplementary structural constraint on the search space, nested NER has a quadratic-time complexity, that is the same asymptotic complexity than the non-nested case. The proposed algorithm covers a large part of three standard English benchmarks and delivers comparable experimental results.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 15 of its 53 references that are in the map. First posted on arXiv 10 Oct 2022.
Builds on
15 of 53 references.
References · 15
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
- 2016Deep Biaffine Attention for Neural Dependency Parsingcited by 334
- 2021A Unified Generative Framework for Various NER Subtaskscited by 141
- 2021Locate and Label: A Two-stage Identifier for Nested Named Entity Recognitioncited by 60
- 2017A Minimal Span-Based Neural Constituency Parsercited by 59
- 2018Differentiable Dynamic Programming for Structured Prediction and Attentioncited by 58
- 2021A Sequence-to-Set Network for Nested Named Entity Recognitioncited by 40
- 2019Nested Named Entity Recognition via Second-best Sequence Learning and Decodingcited by 34
- 2018Neural Segmental Hypergraphs for Overlapping Mention Recognitioncited by 32
- 2020Nested Named Entity Recognition with Partially-Observed TreeCRFscited by 23
- 2019Multi-Grained Named Entity Recognitioncited by 19
3 more
- 2018Labeling Gaps Between Words: Recognizing Overlapping Mentions with Mention Separatorscited by 14
- 2022Nested Named Entity Recognition as Latent Lexicalized Constituency Parsingcited by 14
- 2020Span-based discontinuous constituency parsing: a family of exact chart-based algorithms with time complexities from O(n^6) down to O(n^3)cited by 11
Built on by
Citing papers per year: 2023: 1; 2024: 2.
3 papers.