CLLGMay 4, 2022

Modeling Task Interactions in Document-Level Joint Entity and Relation Extraction

arXiv:2205.01909v1630 citationsh-index: 33
Originality Incremental advance
AI Analysis

This addresses the problem of improving accuracy in document-level information extraction for NLP applications, but it is incremental as it builds on existing multi-task frameworks.

The paper tackles document-level joint entity and relation extraction by modeling the two-way interaction between coreference resolution and relation extraction, introducing Graph Compatibility to bridge task decisions. The result shows up to 2.3/5.1 F1 improvement over baselines on DocRED and DWIE datasets.

We target on the document-level relation extraction in an end-to-end setting, where the model needs to jointly perform mention extraction, coreference resolution (COREF) and relation extraction (RE) at once, and gets evaluated in an entity-centric way. Especially, we address the two-way interaction between COREF and RE that has not been the focus by previous work, and propose to introduce explicit interaction namely Graph Compatibility (GC) that is specifically designed to leverage task characteristics, bridging decisions of two tasks for direct task interference. Our experiments are conducted on DocRED and DWIE; in addition to GC, we implement and compare different multi-task settings commonly adopted in previous work, including pipeline, shared encoders, graph propagation, to examine the effectiveness of different interactions. The result shows that GC achieves the best performance by up to 2.3/5.1 F1 improvement over the baseline.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes