ComputingComputer ScienceComputational LinguisticsMachine LearningNatural Language ProcessingDeep LearningInformation ExtractionMulti-task LearningNamed Entity RecognitionRelation ExtractionBenchmark DatasetsEncoder DesignEncodersJoint Entity ExtractionJoint Entity RecognitionJoint Named Entity RecognitionJoint Relation Extraction
Named entity recognition and relation extraction are fundamental NLP tasks often addressed jointly via table‑filling models that rely on a single encoder to capture shared information. The study proposes that using two distinct encoders can better capture the differing information needed for entity and relation extraction. The authors introduce table‑sequence encoders comprising a table encoder and a sequence encoder that mutually inform representation learning. Experiments demonstrate that the dual‑encoder model outperforms single‑encoder baselines and achieves significant gains on standard datasets.
Named entity recognition and relation extraction are two important fundamental problems. Joint learning algorithms have been proposed to solve both tasks simultaneously, and many of them cast the joint task as a table-filling problem. However, they typically focused on learning a single encoder (usually learning representation in the form of a table) to capture information required for both tasks within the same space. We argue that it can be beneficial to design two distinct encoders to capture such two different types of information in the learning process. In this work, we propose the novel table-sequence encoders where two different encoders – a table encoder and a sequence encoder are designed to help each other in the representation learning process. Our experiments confirm the advantages of having two encoders over one encoder. On several standard datasets, our model shows significant improvements over existing approaches.
49
Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2016 · 222.1K citations · Full text
DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · 2023 · 76.3K citations · Full text