Pith. sign in

REVIEW 4 cited by

Entity, Relation, and Event Extraction with Contextualized Span Representations

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1909.03546 v2 pith:LFFWRMJM submitted 2019-09-08 cs.CL

Entity, Relation, and Event Extraction with Contextualized Span Representations

classification cs.CL
keywords extractionspantasksentityframeworkrepresentationscontextualizedcross-sentence
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We examine the capabilities of a unified, multi-task framework for three information extraction tasks: named entity recognition, relation extraction, and event extraction. Our framework (called DyGIE++) accomplishes all tasks by enumerating, refining, and scoring text spans designed to capture local (within-sentence) and global (cross-sentence) context. Our framework achieves state-of-the-art results across all tasks, on four datasets from a variety of domains. We perform experiments comparing different techniques to construct span representations. Contextualized embeddings like BERT perform well at capturing relationships among entities in the same or adjacent sentences, while dynamic span graph updates model long-range cross-sentence relationships. For instance, propagating span representations via predicted coreference links can enable the model to disambiguate challenging entity mentions. Our code is publicly available at https://github.com/dwadden/dygiepp and can be easily adapted for new tasks or datasets.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. FinTagging: Benchmarking LLMs for Extracting and Structuring Financial Information

    cs.CL 2025-05 unverdicted novelty 7.0

    FinTagging decomposes XBRL tagging into FinNI extraction and FinCL full-taxonomy linking, showing LLMs handle extraction but struggle with fine-grained concept alignment in zero-shot settings.

  2. MedPath: Multi-Domain Cross-Vocabulary Hierarchical Paths for Biomedical Entity Linking

    cs.CL 2025-11 conditional novelty 6.0

    MedPath combines 513k+ expert-annotated biomedical mentions into a UMLS-normalized dataset with cross-vocabulary mappings and hierarchical paths for 11 vocabularies.

  3. EXCEEDS: Extracting Complex Events via Nugget-based Grid Modeling in Scientific Domain

    cs.CL 2024-06 unverdicted novelty 6.0

    Introduces the SciEvents dataset for scientific event extraction and the EXCEEDS nugget-grid modeling framework that reports state-of-the-art results on the new data.

  4. Medical Report Generation: A Hierarchical Task Structure-Based Cross-Modal Causal Intervention Framework

    cs.CV 2025-11 unverdicted novelty 5.0

    HTSC-CIF applies hierarchical task decomposition and cross-modal causal intervention to generate medical reports from images while addressing domain knowledge, alignment, and bias challenges.