DWIE: an entity-centric dataset for multi-task document-level information extraction (2020-09-26T00:00:00.000000Z)

TL;DR

This paper proposes a new entity-driven metric that takes into account the number of mentions that compose each of the predicted and ground truth entities in DWIE, and proposes to use graph-based neural message passing techniques between document-level mention spans to stimulate further research in graph neural networks for representation learning in multi-task IE.

Authors

Klim Zaporojets

2 papers

Johannes Deleu

4 papers

Chris Develder

4 papers

Thomas Demeester

4 papers

TL;DR

Authors

References105 items

Boundaries and edges rethinking: An end-to-end neural model for overlapping entity relation extraction

A Cross-Media Deep Relationship Classification Method Using Discrimination Information

Investigating Query Expansion and Coreference Resolution in Question Answering on BERT

Recipes for Building an Open-Domain Chatbot

An overview of online fake news: Characterization, detection, and discussion

Investigating Entity Knowledge in BERT with Simple Neural End-To-End Entity Linking

Knowledge Enhanced Contextual Word Representations

Entity, Relation, and Event Extraction with Contextualized Span Representations

GraphRel: Modeling Text as Relational Graphs for Joint Entity and Relation Extraction

Coreference Resolution with Entity Equalization

Span-Level Model for Relation Extraction

Attention Guided Graph Convolutional Networks for Relation Extraction

DocRED: A Large-Scale Document-Level Relation Extraction Dataset

Matching the Blanks: Distributional Similarity for Relation Learning

Pooled Contextualized Embeddings for Named Entity Recognition

Interconnected Question Generation with Coreference Alignment and Conversation Flow Modeling

Enriching Pre-trained Language Model with Entity Information for Relation Classification

Language-Conditioned Graph Networks for Relational Reasoning

A general framework for information extraction using dynamic span graphs

Cloze-driven Pretraining of Self-attention Networks

Multi-Task Feature Learning for Knowledge Graph Enhanced Recommendation

News recommender systems - Survey and roads ahead

FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation

How Powerful are Graph Neural Networks?

Graph Convolution over Pruned Dependency Trees Improves Relation Extraction

Semi-Supervised Sequence Modeling with Cross-View Training

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

Contextual String Embeddings for Sequence Labeling

Adversarial training for multi-context joint entity and relation extraction

Automated Fact Checking: Task Formulations, Methods and Future Directions

Nested Named Entity Recognition Revisited

WISER: A Semantic Approach for Expert Finding in Academia based on Entity Linking

An Annotated Corpus for Machine Reading of Instructions in Wet Lab Protocols

Joint entity recognition and relation extraction as a multi-head selection problem

Higher-Order Coreference Resolution with Coarse-to-Fine Inference

Why Reinvent the Wheel: Let's Build Question Answering Systems Together

DKN: Deep Knowledge-Aware Network for News Recommendation

Results of the WNUT2017 Shared Task on Novel and Emerging Entity Recognition

Position-aware Attention and Supervised Data Improve Slot Filling

End-to-End Neural Relation Extraction with Global Optimization

Scientific Information Extraction with Semi-supervised Neural Tagging

End-to-end Neural Coreference Resolution

A review of natural language processing techniques for opinion mining systems

Named Entity Disambiguation for Noisy Text

SemEval 2017 Task 10: ScienceIE - Extracting Keyphrases and Relations from Scientific Publications

Cross-Sentence N-ary Relation Extraction with Graph LSTMs

Reconstructing the house from the ad: Structured prediction on real estate classifieds

Improved Neural Relation Detection for Knowledge Base Question Answering

Reading Wikipedia to Answer Open-Domain Questions

Fast and Accurate Entity Recognition with Iterated Dilated Convolutions

Distant Supervision for Relation Extraction beyond the Sentence Boundary

BioCreative V CDR task corpus: a resource for chemical disease relation extraction

Assessing the state of the art in biomedical relation extraction: overview of the BioCreative V chemical-disease relation (CDR) task

Neural Architectures for Named Entity Recognition

End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF

Named Entity Recognition with Bidirectional LSTM-CNNs

Gated Graph Sequence Neural Networks

Learning Anaphoricity and Antecedent Ranking Features for Coreference Resolution

From Light to Rich ERE: Annotation of Entities, Relations, and Events

GloVe: Global Vectors for Word Representation

A Comparison of the Events and Relations Across ACE, ERE, TAC-KBP, and FrameNet Annotation Standards

Scoring Coreference Partitions of Predicted Mentions: A Reference Implementation

Incremental Joint Extraction of Entity Mentions and Relations

Easy Victories and Uphill Battles in Coreference Resolution

Interrater reliability: the kappa statistic

CoNLL-2012 Shared Task: Modeling Multilingual Unrestricted Coreference in OntoNotes

Robust Disambiguation of Named Entities in Text

Modeling Relations and Their Mentions without Labeled Text

Extending English ACE 2005 Corpus Annotation with Ground-truth Links to Wikipedia

SemEval-2010 Task 8: Multi-Way Classification of Semantic Relations between Pairs of Nominals

Collective annotation of Wikipedia entities in web text

SemEval-2010 Task 8: Multi-Way Classification of Semantic Relations Between Pairs of Nominals

Named Entity Recognition for Question Answering

OntoNotes: The 90% Solution

On Coreference Resolution Performance Metrics

GENIA corpus - a semantically annotated corpus for bio-textmining

Introduction to the CoNLL-2003 Shared Task: Language-Independent Named Entity Recognition