🤖 AI Summary
This work addresses few-shot named entity recognition (NER) by challenging the end-to-end joint modeling paradigm. Drawing on generative grammar theory, we propose a “extract-then-classify” decoupled framework: entity extraction is treated as a syntactic task—requiring no semantic information—while classification is delegated to pre-trained language models (PLMs) or large language models (LLMs) as a semantic task. Empirical analysis reveals that rare words—particularly proper nouns—serve as critical syntactic cues; high-precision extraction is achieved using only shallow syntactic features (e.g., POS tags, dependency relations, and n-grams), with word embeddings or contextualized semantic representations yielding no performance gain. On benchmarks including CoNLL-2003, our extraction module achieves state-of-the-art F1 scores; ablation studies confirm that incorporating semantic features does not improve extraction accuracy. To our knowledge, this is the first study grounding syntactic–semantic separation in formal linguistics, providing both theoretical justification and empirical validation for decoupled modeling, while elucidating the root cause of failures in multi-task joint parsing.
📝 Abstract
Most previous research treats named entity extraction and classification as an end-to-end task. We argue that the two sub-tasks should be addressed separately. Entity extraction lies at the level of syntactic analysis while entity classification lies at the level of semantic analysis. According to Noam Chomsky's "Syntactic Structures," pp. 93-94 (Chomsky 1957), syntax is not appealed to semantics and semantics does not affect syntax. We analyze two benchmark datasets for the characteristics of named entities, finding that uncommon words can distinguish named entities from common text; where uncommon words are the words that hardly appear in common text and they are mainly the proper nouns. Experiments validate that lexical and syntactic features achieve state-of-the-art performance on entity extraction and that semantic features do not further improve the extraction performance, in both of our model and the state-of-the-art baselines. With Chomsky's view, we also explain the failure of joint syntactic and semantic parsings in other works.
