# A General Framework for Information Extraction using Dynamic Span Graphs

arXiv: https://arxiv.org/abs/1904.03296 · HTML: https://mlsanity.com/paper/1904.03296/

## Key facts

- Cited by 93 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Apr 2019.

## Built on by (most cited first, 30 of 93)

- [RadGraph: Extracting Clinical Entities and Relations from Radiology Reports](https://mlsanity.com/paper/2106.14463/) (2021)
- [Structured Prediction as Translation between Augmented Natural Languages](https://mlsanity.com/paper/2101.05779/) (2021)
- [A Unified Generative Framework for Various NER Subtasks](https://mlsanity.com/paper/2106.01223/) (2021)
- [Unified Named Entity Recognition as Word-Word Relation Classification](https://mlsanity.com/paper/2112.10070/) (2021)
- [Learning Span-Level Interactions for Aspect Sentiment Triplet Extraction](https://mlsanity.com/paper/2107.12214/) (2021)
- [Packed Levitated Marker for Entity and Relation Extraction](https://mlsanity.com/paper/2109.06067/) (2021)
- [Text-to-Table: A New Way of Information Extraction](https://mlsanity.com/paper/2109.02707/) (2021)
- [DeepStruct: Pretraining of Language Models for Structure Prediction](https://mlsanity.com/paper/2205.10475/) (2022)
- [Autoregressive Structured Prediction with Language Models](https://mlsanity.com/paper/2210.14698/) (2022)
- [A Sequence-to-Set Network for Nested Named Entity Recognition](https://mlsanity.com/paper/2105.08901/) (2021)
- [UniRE: A Unified Label Space for Entity Relation Extraction](https://mlsanity.com/paper/2107.04292/) (2021)
- [A Span-Based Model for Joint Overlapped and Discontinuous Named Entity Recognition](https://mlsanity.com/paper/2106.14373/) (2021)
- [An End-to-end Model for Entity-level Relation Extraction using Multi-instance Learning](https://mlsanity.com/paper/2102.05980/) (2021)
- [TextEE: Benchmark, Reevaluation, Reflections, and Future Challenges in Event Extraction](https://mlsanity.com/paper/2311.09562/) (2023)
- [A Trigger-Sense Memory Flow Framework for Joint Entity and Relation Extraction](https://mlsanity.com/paper/2101.10213/) (2021)
- [Cross-Task Instance Representation Interactions and Label Dependencies for Joint Information Extraction with Graph Convolutional Networks](https://mlsanity.com/paper/2103.09330/) (2021)
- [A Comprehensive Survey on Relation Extraction: Recent Advances and New Frontiers](https://mlsanity.com/paper/2306.02051/) (2023)
- [BertNet: Harvesting Knowledge Graphs with Arbitrary Relations from Pretrained Language Models](https://mlsanity.com/paper/2206.14268/) (2022)
- [Intent Classification and Slot Filling for Privacy Policies](https://mlsanity.com/paper/2101.00123/) (2021)
- [DaN+: Danish Nested Named Entities and Lexical Normalization](https://mlsanity.com/paper/2105.11301/) (2021)
- [Joint Biomedical Entity and Relation Extraction with Knowledge-Enhanced Collective Inference](https://mlsanity.com/paper/2105.13456/) (2021)
- [CitationIE: Leveraging the Citation Graph for Scientific Information Extraction](https://mlsanity.com/paper/2106.01560/) (2021)
- [Parallel Instance Query Network for Named Entity Recognition](https://mlsanity.com/paper/2203.10545/) (2022)
- [Fusing Heterogeneous Factors with Triaffine Mechanism for Nested Named Entity Recognition](https://mlsanity.com/paper/2110.07480/) (2021)
- [Process-Level Representation of Scientific Protocols with Interactive Annotation](https://mlsanity.com/paper/2101.10244/) (2021)
- [Global Pointer: Novel Efficient Span-based Approach for Named Entity Recognition](https://mlsanity.com/paper/2208.03054/) (2022)
- [Self-Improving for Zero-Shot Named Entity Recognition with Large Language Models](https://mlsanity.com/paper/2311.08921/) (2023)
- [Nested Named Entity Recognition as Latent Lexicalized Constituency Parsing](https://mlsanity.com/paper/2203.04665/) (2022)
- [Human-in-the-loop Evaluation for Early Misinformation Detection: A Case Study of COVID-19 Treatments](https://mlsanity.com/paper/2212.09683/) (2022)
- [PolyIE: A Dataset of Information Extraction from Polymer Material Scientific Literature](https://mlsanity.com/paper/2311.07715/) (2023)

## Abstract (arXiv)

We introduce a general framework for several information extraction tasks that share span representations using dynamically constructed span graphs. The graphs are constructed by selecting the most confident entity spans and linking these nodes with confidence-weighted relation types and coreferences. The dynamic span graph allows coreference and relation type confidences to propagate through the graph to iteratively refine the span representations. This is unlike previous multi-task frameworks for information extraction in which the only interaction between tasks is in the shared first-layer LSTM. Our framework significantly outperforms the state-of-the-art on multiple information extraction tasks across multiple datasets reflecting different domains. We further observe that the span enumeration approach is good at detecting nested span entities, with significant F1 score improvement on the ACE dataset.