Fusing Heterogeneous Factors with Triaffine Mechanism for Nested Named Entity Recognition
Nested entities are observed in many domains due to their compositionality, which cannot be easily recognized by the widely-used sequence labeling framework. A natural solution is to treat the task as a span classification problem. To learn better span representation and increase classification performance, it is crucial to effectively integrate heterogeneous factors including inside tokens, boundaries, labels, and related spans which could be contributing to nested entities recognition. To fuse these heterogeneous factors, we propose a novel triaffine mechanism including triaffine attention and scoring. Triaffine attention uses boundaries and labels as queries and uses inside tokens and related spans as keys and values for span representations. Triaffine scoring interacts with boundaries and span representations for classification. Experiments show that our proposed method outperforms previous span-based methods, achieves the state-of-the-art $F_1$ scores on nested NER datasets GENIA and KBP2017, and shows comparable results on ACE2004 and ACE2005.
Code (1)
Tasks
Classificationnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)NERNested Named Entity RecognitionSimilar Papers 제목 키워드 기반
Fusing Heterogeneous Factors with Triaffine Mechanism for Nested Named Entity Recognition
Nested entities are observed in many domains due to their compositionality, which cannot be easily recognized by the widely-used sequence labeling framework. A natural solution is to treat the task as a span classificati…
Classificationnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)+2Type-supervised sequence labeling based on the heterogeneous star graph for named entity recognition
Named entity recognition is a fundamental task in natural language processing, identifying the span and category of entities in unstructured texts. The traditional sequence labeling methodology ignores the nested entitie…
Graph Attentionnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)+3NestedVAE: Isolating Common Factors via Weak Supervision
Fair and unbiased machine learning is an important and active field of research, as decision processes are increasingly driven by models that learn from data. Unfortunately, any biases present in the data may be learned …
AttributeChange DetectionDecision MakingDiffusion-nested Auto-Regressive Synthesis of Heterogeneous Tabular Data
Autoregressive models are predominant in natural language generation, while their application in tabular data remains underexplored. We posit that this can be attributed to two factors: 1) tabular data contains heterogen…
Text GenerationNetwork nestedness in primates: a structural constraint or a biological advantage of social complexity?
This study investigates the prevalence and implications of nestedness within primate social networks, examining its relationship with cognitive and structural factors. We analysed data from 51 primate groups across 21 sp…