LOGEN:基于自训练的少样本逻辑知识条件文本生成
LOGEN: Few-shot Logical Knowledge-Conditioned Text Generation with Self-training
AI总结:
针对结构化数据自然语言生成存在的内容选择不可控、保真度低,以及现有逻辑知识条件生成方法数据需求量大的问题,本文提出少样本统一框架LOGEN,通过自训练与基于内容结构一致性的伪逻辑形式采样,在少量样本下取得优于基线的性能。
摘要:
从结构化数据生成自然语言的研究主要聚焦于表层描述,存在内容选择不可控、保真度低的问题。已有研究利用逻辑形式推进逻辑知识条件文本生成任务,虽取得显著进展,但这类方法数据需求量大,在数据有限的实际场景中难以落地。为此,本文提出一个少样本场景下逻辑知识条件文本生成的统一框架。仅需少量种子逻辑形式(如20/100样本),该方法便借助自训练机制,基于内容与结构一致性采样伪逻辑形式。实验结果表明,该方法的少样本性能优于各基线模型。
英文摘要:
Natural language generation from structured data mainly focuses on surface-level descriptions, suffering from uncontrollable content selection and low fidelity. Previous works leverage logical forms to facilitate logical knowledge-conditioned text generation. Though achieving remarkable progress, they are data-hungry, which makes the adoption for real-world applications challenging with limited data. To this end, this paper proposes a unified framework for logical knowledge-conditioned text generation in the few-shot setting. With only a few seeds logical forms (e.g., 20/100 shot), our approach leverages self-training and samples pseudo logical forms based on content and structure consistency. Experimental results demonstrate that our approach can obtain better few-shot performance than baselines.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。