Deeper Task-Specificity Improves Joint Entity and Relation Extraction

15 Feb 2020  ·  Phil Crone ·

Multi-task learning (MTL) is an effective method for learning related tasks, but designing MTL models necessitates deciding which and how many parameters should be task-specific, as opposed to shared between tasks. We investigate this issue for the problem of jointly learning named entity recognition (NER) and relation extraction (RE) and propose a novel neural architecture that allows for deeper task-specificity than does prior work. In particular, we introduce additional task-specific bidirectional RNN layers for both the NER and RE tasks and tune the number of shared and task-specific layers separately for different datasets. We achieve state-of-the-art (SOTA) results for both tasks on the ADE dataset; on the CoNLL04 dataset, we achieve SOTA results on the NER task and competitive results on the RE task while using an order of magnitude fewer trainable parameters than the current SOTA architecture. An ablation study confirms the importance of the additional task-specific layers for achieving these results. Our work suggests that previous solutions to joint NER and RE undervalue task-specificity and demonstrates the importance of correctly balancing the number of shared and task-specific parameters for MTL approaches in general.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Relation Extraction Adverse Drug Events (ADE) Corpus Deeper RE+ Macro F1 83.74 # 3
NER Macro F1 89.48 # 7
Relation Extraction CoNLL04 Deeper NER Macro F1 87 # 1
RE+ Micro F1 71.08 # 8
RE+ Macro F1 72.63 # 4
NER Micro F1 89.78 # 5

Methods


No methods listed for this paper. Add relevant methods here