Entity. Relation, and Event Extraction with Contextualized Span Representations

by   David Wadden, et al.

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.


page 1

page 2

page 3

page 4


Pack Together: Entity and Relation Extraction with Levitated Marker

Named Entity Recognition (NER) and Relation Extraction (RE) are the core...

A General Framework for Information Extraction using Dynamic Span Graphs

We introduce a general framework for several information extraction task...

Enhanced Language Representation with Label Knowledge for Span Extraction

Span extraction, aiming to extract text spans (such as words or phrases)...

HySPA: Hybrid Span Generation for Scalable Text-to-Graph Extraction

Text-to-Graph extraction aims to automatically extract information graph...

Eliciting Knowledge from Experts:Automatic Transcript Parsing for Cognitive Task Analysis

Cognitive task analysis (CTA) is a type of analysis in applied psycholog...

Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Construction

We introduce a multi-task setup of identifying and classifying entities,...

Span Classification with Structured Information for Disfluency Detection in Spoken Utterances

Existing approaches in disfluency detection focus on solving a token-lev...