发现编码器对遗漏和错误实体信号变弱，揭示生成模型信息丢失原因。
Probing Omissions and Distortions in Transformer-based RDF-to-Text Models
- 用余弦相似度无参数探测编码器中实体缺失情况。
- 编码器输出能有效识别遗漏与错误实体，表明信息已在编码阶段丢失。
- 适合研究文本生成缺陷、模型可解释性的研究人员参考。
在自然语言生成（NLG）中，重要信息常被遗漏。为理解此类错误的成因，本文聚焦于基于RDF的文本生成任务，提出两种探测方法：(i) 一种基于余弦相似度的无参数探测法，比较完整与移除部分实体后的RDF图嵌入；(ii) 一种参数化二分类探针，用于检测编码器嵌入中被遗漏的实体。同时扩展分析至错误实体（如拼写错误、单位错误等）。实验表明，无论是遗漏还是错误实体，均可在编码器输出嵌入中被有效探测，说明编码器对这些实体的信号较弱，是信息损失的关键环节。该研究证明了探针方法可用于识别NLG模型输出中的错误。
原文摘要 · Abstract (English)
In Natural Language Generation (NLG), important information is sometimes omitted in the output text. To better understand and analyse how this type of mistake arises, we focus on RDF-to-Text generation and explore two methods of probing omissions in the encoder output of BART (Lewis et al, 2020) and of T5 (Raffel et al, 2019): (i) a novel parameter-free probing method based on the computation of cosine similarity between embeddings of RDF graphs and of RDF graphs in which we removed some entities and (ii) a parametric probe which performs binary classification on the encoder embeddings to detect omitted entities. We also extend our analysis to distorted entities, i.e. entities that are not fully correctly mentioned in the generated text (e.g. misspelling of entity, wrong units of measurement). We found that both omitted and distorted entities can be probed in the encoder's output embeddings. This suggests that the encoder emits a weaker signal for these entities and therefore is responsible for some loss of information. This also shows that probing methods can be used to detect mistakes in the output of NLG models.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。