GenKBP_Papers

Label-augmented Text

• Structured Prediction as Translation between Augmented Natural Languages

• Augmented Natural Language for Generative Sequence Labeling

Copy Mechanism

• Extracting Relational Facts by an End-to-End Neural Model with Copy Mechanism

• Learning the Extraction Order of Multiple Relational Facts in a Sentence with Reinforcement Learning

• CopyMTL: Copy Mechanism for Joint Extraction of Entities and Relations with Multi-Task Learning

Generating Word Indices

• A Unified Generative Framework for Various NER Subtasks

• A Unified Generative Framework for Aspect-Based Sentiment Analysis

• Don’t Parse, Generate! A Sequence to Sequence Architecture for Task-Oriented Semantic Parsing

• Effective Modeling of Encoder-Decoder Architecture for Joint Entity and Relation Extraction

Generating Answers

• Event Extraction by Answering (Almost) Natural Questions

• Event Extraction as Machine Reading Comprehension

• Event Extraction as Multi-turn Question Answering

• Can Generative Pre-trained Language Models Serve As Knowledge Bases for Closed-book QA?

• Answer Generation for Retrieval-based Question Answering Systems

Filling Templates

• Document-Level Event Argument Extraction by Conditional Generation

• Template Filling with Generative Transformers

Tagging Texts

• Neural Architectures for Nested NER through Linearization

• Exploring Sequence-to-Sequence Learning in Aspect Term Extraction

Structurelinearized Texts

• Contrastive Information Extraction With Generative Transformer

• Contrastive Triple Extraction with Generative Transformer

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

• Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extraction

• Intent Classification and Slot Filling for Privacy Policies

• Unified Structure Generation for Universal Information Extraction

• Relation Extraction By End-to-end Language generation

• From Discrimination to Generation: Knowledge Graph Completion with Generative Transformer

Non-autogressive

• Joint Entity and Relation Extraction with Set Prediction Networks

• Minimize Exposure Bias of Seq2Seq Models in Joint Entity and Relation Extraction

Ranking Input-output Pairs

• Beyond [CLS] through Ranking by Generation

• Document Ranking with a Pretrained Sequence-to-Sequence Model

• Autoregressive Entity Retrieval

• Template-Based Named Entity Recognition Using BART

Combinations