Span-based joint entity and relation extraction augmented with sequence tagging mechanism
This work addresses a specific bottleneck in joint extraction for NLP tasks, offering incremental improvements over existing span-based models.
The paper tackled the problem of span-based joint entity and relation extraction by proposing a model that incorporates token-level label information, which improved performance over previous methods. Experimental results on three benchmark datasets showed that STSN consistently outperformed the strongest baselines in F1, achieving new state-of-the-art results.
Span-based joint extraction simultaneously conducts named entity recognition (NER) and relation extraction (RE) in text span form. However, since previous span-based models rely on span-level classifications, they cannot benefit from token-level label information, which has been proven advantageous for the task. In this paper, we propose a Sequence Tagging augmented Span-based Network (STSN), a span-based joint model that can make use of token-level label information. In STSN, we construct a core neural architecture by deep stacking multiple attention layers, each of which consists of three basic attention units. On the one hand, the core architecture enables our model to learn token-level label information via the sequence tagging mechanism and then uses the information in the span-based joint extraction; on the other hand, it establishes a bi-directional information interaction between NER and RE. Experimental results on three benchmark datasets show that STSN consistently outperforms the strongest baselines in terms of F1, creating new state-of-the-art results.